https://arxiv.org/api/RYHWZSSFISoQXDHA+bDPuAQi/c4 2026-09-22T01:58:47Z 60 98 0 http://arxiv.org/abs/2609.08105v1 2026-09-08T01:34:39Z

The Indonesian Digital Library of Culture (Perpustakaan Digital Budaya Indonesia, PDBI; budaya-indonesia.org) is a participatory platform that has collected tens of thousands of entries on Nusantara cultural heritage through public contribution since 2007. Manual contribution faces three structural barriers: coverage (knowledge is scattered across languages and sites), integrity (open sources mix authentic documentation with noise), and completeness (subjects are recorded but their data remain shallow). This paper presents a methodological framework for autonomous, AI-based harvesting of cultural knowledge from the open web, designed to expand corpus coverage while intensifying per-entry data depth. The methodology is organised as a five-stage economic funnel: focused crawling, multilingual extraction and canonicalisation, vector encoding with blocking, agentic decision-making, and idempotent publication, under the principle of deterministic orchestration, agentic decisions. Each stage is formalised: funnel economics and optimal filter ordering; crawl-frontier dynamics as a subcritical branching process that explains the necessity of recurrent re-seeding; fact-level novelty via a containment measure; Bayesian multi-source evidence fusion with elevated publication thresholds for sacred categories; exactly-once effects via idempotent upserts and the transactional outbox; sliding-window inference budgeting with a reservation protocol; statistical quality auditing; and seed selection as submodular coverage maximisation. The framework retains four high-value human roles: curator of direction, escalation approver, quality auditor, and guardian of meaning, while machine autonomy is raised in stages. Ethical, legal, and cultural-sensitivity implications are discussed, including the architectural guarantee that the machine never overwrites human contributions.

2026-09-08T01:34:39Z 11 pages, 3 figures Hokky Situngkir http://arxiv.org/abs/2609.04184v1 2026-09-03T17:58:09Z

Declarative UI protocols such as A2UI let applications generate interactive UIs by selecting pre-built components from a catalog and binding their props to application data, rather than emitting frontend code from scratch. This contract is attractive for production systems because of safety and consistency. An open question is: can low-latency and low-cost small models achieve the required quality for A2UI-based UI generation? To answer this, we systematically study three controllable design choices for catalog-conditioned A2UI generation: supervised fine-tuning (SFT) data construction method, model size, and component-catalog size. Across two React/TypeScript domains and four base checkpoints spanning two model families (Qwen 3.5 0.8B/2B/4B; SmolLM 3B), we find: (i) a 4B fine-tuned student recovers ~98% of teacher semantic quality and ~97% of teacher visual quality at more than an order of magnitude lower cost than frontier API calls; (ii) both augmented strategies (Perturbed-catalog and Constrained-GT) Pareto-dominate the unaugmented Full-catalog baseline, while specializing on different axes; (iii) even small models can handle and benefit from relatively large component catalog size. We distill these results into practitioner-facing trade-offs and deployment recommendations across the three design choices.

2026-09-03T17:58:09Z Yingxiang Yang Weihang Xiao Ben Bullough Tushar Deshpande Niresh Agarwal 10.1145/3844177.3844556 http://arxiv.org/abs/2608.25565v1 2026-08-26T09:19:17Z

Generative user interfaces (GenUIs) promise on-demand components tailored to users' needs. As users iterate on information tasks, they construct personal structures over information they encounter---how items are grouped, what gets prioritized, and what terms mean in their context. Yet, current systems leave these structural decisions to the model at each generation, ignoring the structural logic users have established. Without a persistent representational structure shared between user and system, GenUIs have no basis to remain aligned with what users have established. We draw on Information Architecture (IA), a design practice for organizing and structuring information, as a shared language to bridge user-constructed structure and system generation. We present a framework identifying four IA elements---partition, hierarchy, order, and vocabulary---and characterize how each maps to concrete UI generation decisions. We instantiate this framework in Maru, a conversational system that captures user prompts and interactions as IA preferences, persisting as rules both user and system draw on across generations. A user study revealed that IA persistence kept generated UIs aligned as sessions progressed, while alignment without it degraded, with diverse patterns emerging across users and contexts, pointing to the value of IA persistence in aligning GenUI to individual needs.

2026-08-26T09:19:17Z Eunhye Kim DaEun Choi Bryan Min Hyunjung Yi Yue Jiang Juho Kim 10.1145/3830398.3830621 http://arxiv.org/abs/2608.12518v1 2026-08-12T18:51:17Z

Multimodal Large Language Models (MLLMs) have been increasingly adopted to automate webpage generation from visual designs (e.g., screenshots). However, existing evaluations are limited to visual fidelity assessment under a fixed browser-device configuration. Such a setting overlooks the cross-environment rendering compatibility for real-world deployments. To address this gap, we present the first systematic empirical study of cross-environment compatibility in AI-generated webpages. Specifically, we construct WebCompat, a dataset of 2,032 annotated instances, comprising webpages generated by 8 representative AI tools, each rendered across 9 browser-and-device combinations. We analyze the prevalence of compatibility issues, their user-perceptible symptoms, and underlying code-level root causes. Our findings reveal that 68% of generated webpages exhibit at least one compatibility issue, underscoring the pervasive reliability concerns surrounding MLLM-generated front-end artifacts. The most prevalent symptoms are failures that disrupt the entire page layout (88.3%): pages shrink directly to fit the target screen with too small fonts, or exhibit scale mismatches that produce cut-off content. Failures localized to individual elements, such as image distortion or missing components, are comparatively less common (13.4%). Furthermore, although most MLLMs incorporate responsive design patterns into the generation, they fail to properly implement these codes. Guided by the findings, we develop XCompat, a lightweight offline compatibility issue detector that combines visual screenshots and the structural DOM tree for analysis. It achieves an F1 score of 0.903 on the WebCompat-test, outperforming the existing compatibility checking tools and LLM baselines. All datasets and tools are released to support future research on rendering reliability in MLLM-based front-end code generation.

2026-08-12T18:51:17Z Ziyun Guo Jingyu Xiao Yuqiang Sun Yintong Huo http://arxiv.org/abs/2608.09573v1 2026-08-10T13:07:40Z

Natural-language-driven "vibe coding" enables the one-shot generation of visually rich and interactive web applications, yet reliable assessment of their quality has not kept pace. Existing evaluations often score isolated artifacts or final task outcomes, offering limited evidence about which failures occur and why. We introduce VideoVIBE, a video-grounded benchmark that transforms human-operated webpage recordings into fine-grained diagnostic tasks. It contains approximately 1.7K diagnostic Video QA instances derived from 6,338 verified failures across generated webpages, spanning semantic-logical, visual-motion, structural-temporal, and functional failures. Diagnoses are grounded primarily in recorded presentation and behavior, with webpage source code used as complementary context. We further propose V2Lens, a training-free, evidence-grounded multi-agent system that challenges and selectively refines initial video-based diagnoses through targeted visual and source-code verification. Across thirteen closed-source and open-weight Video MLLMs, Gemini-2.5-Flash is the strongest standalone model with a score of 64.54, while V2Lens reaches 71.72, an improvement of 7.18 points. Together, our results show that video-grounded evaluation can move beyond isolated artifacts and aggregate outcomes toward a behaviorally faithful and diagnostically informative account of generated application quality.

2026-08-10T13:07:40Z Jiajun Xu Yanghao Zhou Jingyun Liao Yu Bai Jinxing Zhou Chengliang Liu Changsen Yuan Bo Wang Qian Liu http://arxiv.org/abs/2608.03474v1 2026-08-04T11:14:00Z

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tasks spanning 16 vertical domains. To construct deterministic repair trajectories without costly turn-level human annotation, we develop a scalable Reverse-Corruption Trajectory Engine that iteratively injects structural and stylistic defects into golden pages. We further propose a dual-axis evaluation protocol that measures target-region fidelity and the preservation of unaffected content, where regional reconstruction is assessed by a 5-dimensional VLM-based rubric and localized modification by deterministic pixel-grounded alignment. Experiments on 13 frontier coding agents reveal that current agents struggle to faithfully reconstruct target regions while preserving unaffected content, lack fine-grained visual-code alignment for localized edits, and suffer from error snowballing over multiple turns. Beyond benchmarking, our deterministic evaluation metrics provide fine-grained feedback signals that may facilitate future research on training iterative UI coding agents. Our evaluation code and data will soon be released.

2026-08-04T11:14:00Z Qiming Li Shujie Hu Haohan Liu Xiaocheng Feng Songxiang Liu Guanglu Wan http://arxiv.org/abs/2607.22928v2 2026-07-31T22:01:55Z

Generative UI tools promise to democratize UI design by turning natural language descriptions into complete interfaces. Alongside the interface, these tools generate user-facing design rationales that explain their layout, accessibility, and design choices. However, it remains unclear whether these stated rationales are actually reflected in the interfaces they produce. We call this disconnect ``Design Theater'': plausible and confident design rationales that have little relationship to the actual implementation. To study this phenomenon, we introduce a benchmark and three metrics for measuring Design Theater. The benchmark includes 24 UI generation tasks spanning structural, styling, and functional design requirements. Using this benchmark, we evaluate 120 interfaces created by five generative UI tools. On average, over 25\% of user-facing design rationales are not implemented in the generated interface, and the implementation failure increases to 34\% for functional requirements. Tools recognize roughly half of the UX principles embedded in prompts (mean = 0.54), with four of five tools implementing 6\% or fewer functional principles. We also measure interface similarity across tools and find convergence in visual appearance and layout organization, with greater variation in color choices. Overall, we contribute: 1) the concept of Design Theater; 2) a benchmark with metrics for assessing whether the stated reasoning of generative UI tools is reflected in their implementations; 3) and findings from a systematic evaluation of these tools. We discuss what these findings mean for the design and evaluation of generative UI tools.

2026-07-24T21:57:09Z Accepted at AAAI/AIES Kashif Imteyaz Kaif Imteyaz Nakul Rajpal Kaif Shaikh Michael Muller Saiph Savage http://arxiv.org/abs/2607.12056v1 2026-07-13T18:16:58Z

Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and carry out parts of the purchasing process for users. Website design must now support both human and agent-mediated interaction. This paper introduces the agent-ready website, a design framework for enhancing the readability, interpretability, verifiability, and actionability of e-commerce platforms for AI agents. Existing web design, SEO, and generative engine optimization (GEO) metrics do not fully assess a website's capacity for agent-mediated interaction. The proposed framework is structured around three dimensions agent interpretability, agent executability, and agent decision reliability supported by features such as machine readability, semantic clarity, agent actionability, and contextual decision-reliability signals. The framework is evaluated through a controlled experiment comparing a human-oriented baseline and an agent-ready version of an identical website prototype, with identical catalogs, pricing, stock, and shopping workflows. The evaluation involved five tasks, three browser-agent models (GPT-4.1, Gemini-2.5 Flash, and Grok-4 Fast), and 300 runs, measuring PASS,PARTIAL,FAIL outcomes, strict and functional success rates, error patterns, step counts, and token consumption. The agent-ready website achieved 134 PASS runs out of 150 versus 74 out of 150 for the baseline (strict success rates of 89.3% vs. 49.3%), with the largest gains in product detail extraction, comparison, and multi-constraint selection. It also reduced PARTIAL outcomes from 43 to 3 and lowered the average step count from 9.31 to 6.49. These results provide preliminary evidence that enhanced structural clarity, action cues, evidence signals, and temporal validity indicators can substantially improve the reliability and efficiency of AI browser agents.

2026-07-13T18:16:58Z Said Elnaffar Farzad Rashidi http://arxiv.org/abs/2607.10405v2 2026-07-26T02:38:03Z

Controlling attributes is a critical step toward achieving the final creative outcome, yet current approaches fall short in supporting users in the iterative refinement of generative content. We propose Spatula, a proof-of-concept system that generates on-demand, in-situ attribute control interfaces and interactions for creating motion graphics. Building on a technical probe that automatically analyzes animation context and generates corresponding attributes and UI, we frame attribute control as an explorable landscape and explore the attribute control space along four key dimensions: Discoverability, Resolution, Scope, and Expandability. Findings from a user study (N=12) show that our system provides intuitive and convenient interactions while supporting diverse needs for fine-grained parameter control. Furthermore, our applications demonstrate that the plug-and-play design generalizes to other domains, such as web design and 3D modeling.

2026-07-11T17:10:44Z Boyu Li Linjie Qiu Lin-Ping Yuan Duotun Wang Yue Jiang Zeyu Wang Hongbo Fu http://arxiv.org/abs/2607.00693v2 2026-08-04T09:18:30Z

On October 17th, 2025, Google announced the retirement of most Privacy Sandbox APIs, concluding nearly five years of experimentation with its alternative to privacy-invasive data collection on the Web. Designed to balance privacy with advertising functionality and cross-site tracking, the initiative faced repeated redesigns and limited ecosystem support. In this work, we present the first longitudinal, consent-aware measurement of the Privacy Sandbox's deployment across the Web. Using a custom call listener and weekly crawls of the top-10,000 websites, we monitor the usage of all major APIs in the months preceding their retirement. Adoption had already stagnated well before Google's announcement: most APIs were used by only a handful of actors, whose activity declined steadily throughout our study. Even the APIs that Google plans to maintain show no sign of growth. The sole exception is Cookies Having Independent Partitioned State (CHIPS). Overall, the demise of the Privacy Sandbox leaves unresolved the challenge of enabling privacy-preserving interest-based advertising.

2026-07-01T09:43:46Z Rachid Youssef Grib Alberto Verna Nikhil Jha Martino Trevisan Marco Mellia 10.1145/3830454.3832633 http://arxiv.org/abs/2606.27330v1 2026-06-25T17:44:48Z

Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source MLLMs are cost efficient and privacy preserving compared with commercial large models, they suffer from weak planning and limited cross website generalization. To address these limitations, we introduce the planning experience exploration and utilization (PEEU) method, which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high level training data. To quantitatively analyze the generalization behaviors driving this performance, we propose the task decomposition hierarchical analysis framework (TDHAF) to systematically study compositional generalization across three task granularities: low, middle and high levels. Our analysis reveals that mastering low level atomic skills does not guarantee high level planning competence, while high level task training yields stronger OOD generalization. Experiments on real world benchmarks demonstrate PEEU's superior effectiveness: our 7B model achieves 30.6% accuracy, outperforming the much larger Qwen2.5-VL-32B model. These demonstrate constructing hindsight high level tasks and leveraging experiences is crucial for OOD planning abilities of small MLLMs.

2026-06-25T17:44:48Z Accepted to ACL 2026 Main Tianyi Men Zhuoran Jin Pengfei Cao Yubo Chen Kang Liu Jun Zhao http://arxiv.org/abs/2606.17727v1 2026-06-16T09:43:12Z

Recent vision-language models (VLMs) have shown promising progress in generating webpages from visual inputs, yet existing evaluations mainly focus on short, single-screen, and largely static webpages. We introduce LongWebBench, a benchmark for evaluating long-horizon webpage generation from both structural and functional perspectives. LongWebBench contains 490 real-world long webpages for structural fidelity evaluation and 507 goal-oriented interaction tasks over 129 webpages for functional evaluation. It employs two complementary protocols: a multi-dimensional VLM-based metric for assessing long-range structural coherence, and a DOM-augmented agent-based pipeline for end-to-end functional verification. We further examine the automatic evaluation protocols through human agreement analysis. Experiments with state-of-the-art open-source and proprietary VLMs under single-image and multi-image settings reveal that structural fidelity degrades as webpage length increases, while visually plausible generations often fail to support executable multi-step interactions. These results highlight the need to evaluate long webpage generation beyond visual similarity, with executable interaction as a core criterion. Our code and data are available at https://github.com/zheny2751-dotcom/LongWebBench.

2026-06-16T09:43:12Z 49 pages, 38 figures Yi Zhao Zhen Yang Mengpan Chen Mingde Xu Shanghui Gong Xijun Liu Jibing Gong Jie Tang http://arxiv.org/abs/2606.01022v1 2026-05-31T05:25:14Z

Crafting a product display webpage from a source product image, along with layout and visual content instructions, holds significant practical value for domains such as marketing, advertising, and E-commerce. Intuitively, this task demands strict visual consistency across product displays and high-fidelity instruction following to jointly generate renderable HTML code. These requirements on controllability and instruction-following are closely aligned with the core features of advanced multimodal generative models, such as image editing models and unified models. To this end, this paper introduces ProductWebGen to systematically benchmark the product webpage generation capacities of these models. We organize ProductWebGen with 500 test samples covering 13 product categories; each sample consists of a source image, a visual content instruction, and a webpage instruction. The task is to generate a product showcase webpage including multiple consistent images in accordance with the source image and instructions. Given the mixed-modality input-output nature of the task, we design and systematically compare two workflows for evaluation -- one uses large language models and image editing models to separately generate HTML code and images (editing-based), while the other relies on a single UM to generate both, with image generation conditioned on the preceding multimodal context (UM-based). Empirical results show that editing-based approaches achieve leading results in webpage instruction following and content appeal, while UM-based ones may display more advantages in fulfilling visual content instructions. We also construct a supervised fine-tuning dataset, ProductWebGen-1k, with 1,000 groups of real product images and LLM-generated HTML code. We verify its effectiveness on the open-source UM BAGEL. The data and code are available at https://github.com/SJTU-DENG-Lab/ProductWebGen.

2026-05-31T05:25:14Z Accepted by KDD 2026 Zhihong Liu Siqi Kou Zheng Li Ye Ma Quan Chen Peng Jiang Kai Yu Zhijie Deng 10.1145/3770855.3817507 http://arxiv.org/abs/2606.00530v3 2026-08-13T19:42:37Z

Research on automating software testing has spanned several decades. Most existing approaches generate unit tests for individual methods, validate isolated API endpoints, or target user interface (UI) layers, with non-API and non-UI generators typically exercising only a single focal method. Recent empirical evidence shows a substantial gap between such generated tests and developer-written ones, which often span several focal classes and methods, involve multi-step call sequences, and contain chained assertions, all characteristics that current approaches fail to capture. To address this gap, we propose generating tests from natural language (NL) descriptions of developer intent, an expressive and accessible medium for specifying complex test scenarios. We present Sakura, the first agent-based framework for generating structurally complex tests from NL descriptions. Sakura decomposes NL descriptions into structured blocks and processes them with a multi-agent system: a localization agent grounds test steps in concrete application code via static analysis, a composition agent synthesizes compilable test code and iteratively refines it using execution feedback, and a supervisor agent coordinates their interactions. To evaluate Sakura, we curate a novel dataset of NL test descriptions at three levels of abstraction, reflecting different end-user personas, systematically derived from developer-written tests in Apache Commons projects. Across 20 applications and 1,464 test scenarios, Sakura substantially outperforms off-the-shelf agentic tools such as Gemini CLI instantiated with multiple LLMs, achieving 50-78% higher test compilability and 38-66% higher coverage overlap with ground-truth tests using the same models. Moreover, Sakura paired with small open-source models such as Devstral Small 2 and Qwen3-Coder outperforms Gemini CLI using large proprietary models, at lower cost.

2026-05-30T04:49:10Z 25 pages, 11 figures. Accepted to ISSTA 2026 Tyler Stennett Rangeet Pan Bridget McGinn Alessandro Orso Saurabh Sinha 10.1145/3832112 http://arxiv.org/abs/2605.23657v2 2026-05-28T04:39:19Z

Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill ecosystem rapidly expands, it remains unclear how different models and agent frameworks interact with skills, how to evaluate skill quality, and how users should select skills under practical cost-performance trade-offs. In this paper, we present \textsc{OpenSkillEval}, an automatic evaluation framework for both skill-augmented agent systems and the skills themselves. Instead of relying on static benchmarks, \textsc{OpenSkillEval} automatically constructs realistic task instances from evolving real-world artifacts across five categories of downstream applications: presentation generation, front-end web design, poster generation, data visualization, and report generation. It further collects and organizes community-contributed skills for controlled comparison under unified task settings. Using more than 600 dynamically generated task instances and 30 open-source skills, we conduct a systematic evaluation of state-of-the-art models and agent frameworks. Our results show that skill availability does not guarantee effective skill usage, that the benefit of skill augmentation depends strongly on both the underlying model and the agent framework, and that many publicly popular skills do not consistently outperform base agents without skills. These findings highlight the need for dynamic, task-grounded evaluation and provide practical insights into the design, selection, and deployment of skills for LLM agents. Additional cases and benchmark resources are available on the project website: https://yingjiahao14.github.io/OpenSkillEval-Web/.

2026-05-22T14:09:41Z Jiahao Ying Boxian Ai Wei Tang Siyuan Liu Yixin Cao http://arxiv.org/abs/2605.04165v1 2026-05-05T18:02:31Z

While large language models (LLMs) and coding agents are often applied to user interface (UI) development, developers find it difficult to reliably assess their proficiency in visual and interaction design. Existing evaluations either rely on human experts, who can accurately assess usability by testing critical flows but are slow and costly, or on automated judges, which are scalable but less accurate and opaque. We present FlowEval, a reference-based framework that measures whether a generated UI supports realistic interaction flows by comparing navigation traces from real websites to traces from generated analogs using reference-based similarity metrics (e.g., dynamic time warping). In a small-scale study with expert UI evaluators, we show that reference-based metrics strongly correlate with human judgments, suggesting that they can provide scalable yet trustworthy evaluation for UI generation systems.

2026-05-05T18:02:31Z Jason Wu Priyan Vaithilingam Eldon Schoop Jeffrey Nichols Titus Barik http://arxiv.org/abs/2604.27419v1 2026-04-30T04:49:34Z

With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing benchmarks rely on idealized assumptions, especially for well-structured, information-rich inputs and static execution settings. In contrast, real-world development is constrained by a critical bottleneck: the semantic misalignment between ambiguous, low-quality instructions from non-expert users and model understanding, which results in a failure mode that we term blind execution. To address this gap, we introduce InteractWeb-Bench, the first multimodal interactive benchmark for website generation under non-expert low-code user conditions. InteractWeb-Bench introduces four types of user agents and persona-driven instruction perturbations to systematically simulate diverse user behaviors, including ambiguity, redundancy, and contradiction, grounded in requirement engineering defect taxonomies. We develop an interactive execution environment for agents, featuring a unified action space comprising Clarify, Implement, Verify, and Submit, enabling iterative intent refinement, code synthesis, and visual feedback-based validation. Extensive experiments and analysis reveal that frontier MLLM-based agents remain trapped in blind execution, exposing limitations in intent recognition and adaptive interaction.

2026-04-30T04:49:34Z 21 pages, 13 figures, 7 tables Qiyao Wang Haoran Hu Longze Chen Hongbo Wang Hamid Alinejad-Rokny Yuan Lin Min Yang http://arxiv.org/abs/2604.20398v1 2026-04-22T10:04:46Z

While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain highly challenging. Existing works are often limited to single-page static websites, while agentic frameworks typically rely on multi-turn execution with proprietary models, leading to substantial token costs, high latency, and brittle integration. Training a small LLM end-to-end with reinforcement learning (RL) is a promising alternative, yet it faces a critical bottleneck in designing reliable and computationally feasible rewards for website generation. Unlike single-file coding tasks that can be verified by unit tests, website generation requires evaluating inherently subjective aesthetics, cross-page interactions, and functional correctness. To this end, we propose WebGen-R1, an end-to-end RL framework tailored for project-level website generation. We first introduce a scaffold-driven structured generation paradigm that constrains the large open-ended action space and preserves architectural integrity. We then design a novel cascaded multimodal reward that seamlessly couples structural guarantees with execution-grounded functional feedback and vision-based aesthetic supervision. Extensive experiments demonstrate that our WebGen-R1 substantially transforms a 7B base model from generating nearly nonfunctional websites into producing deployable, aesthetically aligned multi-page websites. Remarkably, our WebGen-R1 not only consistently outperforms heavily scaled open-source models (up to 72B), but also rivals the state-of-the-art DeepSeek-R1 (671B) in functional success, while substantially exceeding it in valid rendering and aesthetic alignment. These results position WebGen-R1 as a viable path for scaling small open models from function-level code generation to project-level web application generation.

2026-04-22T10:04:46Z Juyong Jiang Chenglin Cai Chansung Park Jiasi Shen Sunghun Kim Jianguo Li Yue Wang http://arxiv.org/abs/2604.15309v1 2026-04-16T17:59:49Z

The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flexible and increasingly adopted paradigm for modern UI/UX. However, directly integrating such tools into automated webpage generation often leads to style inconsistency and poor global coherence, as elements are generated in isolation. We propose MM-WebAgent, a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection. MM-WebAgent jointly optimizes global layout, local multimodal content, and their integration, producing coherent and visually consistent webpages. We further introduce a benchmark for multimodal webpage generation and a multi-level evaluation protocol for systematic assessment. Experiments demonstrate that MM-WebAgent outperforms code-generation and agent-based baselines, especially on multimodal element generation and integration. Code & Data: https://aka.ms/mm-webagent.

2026-04-16T17:59:49Z Yan Li Zezi Zeng Yifan Yang Yuqing Yang Ning Liao Weiwei Guo Lili Qiu Mingxi Cheng Qi Dai Zhendong Wang Zhengyuan Yang Xue Yang Ji Li Lijuan Wang Chong Luo http://arxiv.org/abs/2603.13036v1 2026-03-13T14:45:04Z

Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to complex structural tasks like web design. As lay creators increasingly turn to LLMs to 'vibe-code' websites -- prompting for aesthetic and functional goals rather than writing code -- they may inadvertently narrow the diversity of their designs, and limit creative expression throughout the internet. In this paper, we interrogate the possibility of design homogenization in web vibe coding. We first characterize the vibe coding lifecycle, pinpointing stages where homogenization risks may arise. We then conduct a sociotechnical risk analysis unpacking the potential harms of web vibe coding and their interaction with design homogenization. We identify that the push for frictionless generation can exacerbate homogenization and its harms. Finally, we propose a mitigation framework centered on the idea of productive friction. Through case studies at the micro, meso, and macro levels, we show how centering productive friction can empower creators to challenge default outputs and preserve diverse expression in AI-mediated web design.

2026-03-13T14:45:04Z Donghoon Shin Alice Gao Rock Yuren Pang Jaewook Lee Katharina Reinecke Emily Tseng http://arxiv.org/abs/2603.13391v1 2026-03-11T07:48:23Z

Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essential for faithful webpage recreation. Despite this potential, video-conditioned webpage generation remains largely unexplored, with no dedicated benchmark for this task. To fill this gap, we introduce WebVR, a benchmark that evaluates whether MLLMs can faithfully recreate webpages from demonstration videos. WebVR contains 175 webpages across diverse categories, all constructed through a controlled synthesis pipeline rather than web crawling, ensuring varied and realistic demonstrations without overlap with existing online pages. We also design a fine-grained, human-aligned visual rubric that evaluates the generated webpages across multiple dimensions. Experiments on 19 models reveal substantial gaps in recreating fine-grained style and motion quality, while the rubric-based automatic evaluation achieves 96% agreement with human preferences. We release the dataset, evaluation toolkit, and baseline results to support future research on video-to-webpage generation.

2026-03-11T07:48:23Z Yuhong Dai Yanlin Lai Mitt Huang Hangyu Guo Dingming Li Hongbo Peng Haodong Li Yingxiu Zhao Haoran Lyu Zheng Ge Xiangyu Zhang Daxin Jiang http://arxiv.org/abs/2603.04949v3 2026-09-12T06:26:13Z

As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We introduce TimeWarp, a benchmark that emulates the evolving web. TimeWarp consists of three web environments, each with six UI versions spanning UI design, frontend code, and workflows from different eras of the internet. We pair TimeWarp with a set of complex, realistic tasks covering different forms of web navigation. Our experiments reveal that vision-based agents are vulnerable to changes, while text-based agents become brittle once fine-tuned on a single version. To address this, we propose TimeTraj, a new annotation method that uses plan distillation to collect trajectories across multiple versions. By training agents on teacher rollouts using our BC-variant, we achieve substantial performance gains: 20.4% to 37.7% for Qwen-3 4B and 0% to 27.0% for Llama-3.1 8B models. Our work helps study generalization across web designs and opens a new paradigm for collecting plans rather than trajectories to improve the robustness of web agents.

2026-03-05T08:43:06Z Md Farhan Ishmam Kenneth Marino http://arxiv.org/abs/2604.09577v1 2026-02-24T19:42:26Z

AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown "wall of text". Generative UI is a long standing promise, where the model generates not just the content, but the interface itself. Until now, Generative UI was not possible in a robust fashion. We demonstrate that when properly prompted and equipped with the right set of tools, a modern LLM can robustly produce high quality custom UIs for virtually any prompt. When ignoring generation speed, results generated by our implementation are overwhelmingly preferred by humans over the standard LLM markdown output. In fact, while the results generated by our implementation are worse than those crafted by human experts, they are at least comparable in 50% of cases. We show that this ability for robust Generative UI is emergent, with substantial improvements from previous models. We also create and release PAGEN, a novel dataset of expert-crafted results to aid in evaluating Generative UI implementations, as well as the results of our system for future comparisons. Interactive examples can be seen at https://generativeui.github.io

2026-02-24T19:42:26Z Yaniv Leviathan Cheenu Dani Valevski Cheenu Matan Kalman Cheenu Danny Lumen Cheenu Eyal Segalis Cheenu Eyal Molad Cheenu Shlomi Pasternak Cheenu Vishnu Natchu Cheenu Valerie Nygaard Cheenu Srinivasan Cheenu Venkatachary James Manyika Yossi Matias http://arxiv.org/abs/2602.19243v1 2026-02-22T15:55:13Z

Creating webpages requires generating content and arranging layout while iteratively refining both to achieve a coherent design, a process that can be challenging for blind individuals. To understand how blind designers navigate this process, we conducted two rounds of co-design sessions with blind participants, using design probes to elicit their strategies and support needs. Our findings reveal a preference for content and layout to co-evolve, but this process requires external support through cues that situate local elements within the broader page structure as well as multimodal interactions. Building on these insights, we developed TangibleSite, an accessible web design tool that provides real-time multimodal feedback through tangible, auditory, and speech-based interactions. TangibleSite enables blind individuals to create, edit, and reposition webpage elements while integrating content and layout decisions. A formative evaluation with six blind participants demonstrated that TangibleSite enabled independent webpage creation, supported refinement across content and layout, and reduced barriers to achieving visually consistent designs.

2026-02-22T15:55:13Z Jiasheng Li Zining Zhang Zeyu Yan Matthew Wong Arnav Mittal Ge Gao Huaishu Peng 10.1145/3772318.3791895 http://arxiv.org/abs/2602.13363v1 2026-02-13T12:12:53Z

Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about solutions to problems, make changes that impact those environments, and understand how their actions impacted their environment. One of the most common applications of these LLM Agents is in computer programming, where agents can successfully work alongside humans to generate code while controlling programming environments or networking systems. However, with the increasing ability and complexity of these agents comes dangers about the potential for their misuse. A concerning application of LLM agents is in the domain cybersecurity, where they have the potential to greatly expand the threat imposed by attacks such as social engineering. This is due to the fact that LLM Agents can work autonomously and perform many tasks that would normally require time and effort from skilled human programmers. While this threat is concerning, little attention has been given to assessments of the capabilities of LLM coding agents in generating code for social engineering attacks. In this work we compare different LLMs in their ability and willingness to produce potentially dangerous code bases that could be misused by cyberattackers. The result is a dataset of 200 website code bases and logs from 40 different LLM coding agents. Analysis of models shows which metrics of LLMs are more and less correlated with performance in generating spear-phishing sites. Our analysis and the dataset we present will be of interest to researchers and practitioners concerned in defending against the potential misuse of LLMs in spear-phishing.

2026-02-13T12:12:53Z 18 Pages, 7 Figures, 1 Table. Accepted to the conference Human Computer Interaction International Tailia Malloy Tegawende F. Bissyande http://arxiv.org/abs/2604.03235v1 2026-01-30T21:25:00Z

Is it coral, salmon, or peach? What seems like a simple color can have many names, and without a standard, these variations create confusion across design, technology, and communication. Color naming is a fundamental task across industries such as fashion, cosmetics, web design, and visualization tools. However, the lack of universally accepted color naming standards leads to inconsistent color standards across platforms, applications, and industries. Moreover, these systems include hundreds or thousands of overlapping, perceptually indistinct shades, despite the fact that humans typically distinguish only a limited number of unique color categories in practice. In this study, we propose a clustering-based multisource data framework to build a standardized color-naming system. We collected a dataset of over 19,555 RGB values paired with color names from 20 diverse sources. After data cleaning and normalization, we converted the colors to the perceptually uniform CIELAB color space and applied K-means clustering using the CIEDE2000 color difference metric, identifying 280 optimal clusters. For each cluster, we performed a frequency analysis of the associated names to assign representative labels. The resulting system reflects naturally occurring linguistic patterns. We demonstrate its effectiveness in automatic annotation and content-based image retrieval on a clothing dataset. This approach opens new opportunities for standardized, perceptually grounded color labeling in practical applications such as generative AI, visual search, and design systems.

2026-01-30T21:25:00Z Submitted to Wiley for consideration Aruzhan Sabitkyzy Maksat Shagyrov Pakizar Shamoi http://arxiv.org/abs/2601.19171v2 2026-02-09T01:35:44Z

While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine results-creating gulfs of execution and evaluation. To understand the information needed for UI generation, we conducted a thematic analysis of UI prompting guidelines, identifying key design semantics and discovering that they are hierarchical and interdependent. Leveraging these findings, we developed a system that enables users to specify semantics, visualize relationships, and extract how semantics are reflected in generated UIs. By making semantics serve as an intermediate representation between human intent and AI output, our system bridges both gulfs by making requirements explicit and outcomes interpretable. A comparative user study suggests that our approach enhances users' perceived control over intent expression and outcome interpretation, and facilitates more predictable iterative refinement. Our work demonstrates how explicit semantic representation enables systematic and explainable exploration of design possibilities in AI-driven UI design.

2026-01-27T04:01:53Z In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26) Seokhyeon Park Soohyun Lee Eugene Choi Hyunwoo Kim Minkyu Kweon Yumin Song Jinwook Seo 10.1145/3772318.3791966 http://arxiv.org/abs/2601.17614v1 2026-01-24T22:32:56Z

Designing user interfaces that align with user preferences is a time-consuming process, which requires iterative cycles of prototyping, user testing, and refinement. Recent advancements in LLM-based UI generation have enabled efficient UI generation to assist the UI design process. We introduce AlignUI, a method that aligns LLM-generated UIs with user tasks and preferences by using a user preference dataset to guide the LLM's reasoning process. The dataset was crowdsourced from 50 general users (the target users of generated UIs) and contained 720 UI control preferences on eight image-editing tasks. We evaluated AlignUI by generating UIs for six unseen tasks and conducting a user study with 72 additional general users. The results showed that the generated UIs closely align with multiple dimensions of user preferences. We conclude by discussing the applicability of our method to support user-aligned UI design for multiple task domains and user groups, as well as personalized user needs.

2026-01-24T22:32:56Z Yimeng Liu Misha Sra Chang Xiao http://arxiv.org/abs/2601.08859v3 2026-09-14T09:48:40Z

Researchers face a persistent barrier when applying computational algorithms with parameter configuration typically demanding programming skills, interfaces differing across environments, and settings rarely persisting between sessions. This fragmentation forces repetitive input, slows iterative exploration, and undermines reproducibility because parameter choices are difficult to record, share, and reuse. We present EZInput, a cross-runtime environment Python library enabling algorithm developers to automatically generate graphical user interfaces that make their computational tools accessible to end-users without programming expertise. EZInput employs a declarative specification system where developers define input requirements and validation constraints once; the library then handles environment detection, interface rendering, parameter validation, and session persistence across Jupyter notebooks, Google Colab, and terminal environments. This "write once, run anywhere" architecture enables researchers to prototype in notebooks and deploy identical parameter configurations for batch execution on remote systems without code changes or manual transcription. Parameter persistence, inspired by ImageJ/FIJI and adapted to Python workflows, saves and restores user configurations via lightweight YAML files, eliminating redundant input and producing shareable records that enhance reproducibility. EZInput supports diverse input types essential for scientific computing and it also includes built-in validation that ensures data integrity and clear feedback that reduces user friction.

2026-01-07T11:31:34Z Bruno M. Saraiva Iván Hidalgo-Cenalmor António D. Brito Damián Martínez Tayla Shakespeare Guillaume Jacquemet Ricardo Henriques http://arxiv.org/abs/2601.00592v1 2026-01-02T06:43:35Z

Ensuring digital accessibility is essential for inclusive access to online services. However, many government and non-government websites that provide critical services - such as education, healthcare, and public administration - continue to exhibit significant accessibility and usability barriers. This study evaluates the accessibility of Bangladeshi government and non-government websites under WCAG~2.2 by combining automated accessibility assessments with user-reported feedback. A total of 212 websites were analyzed using multiple automated tools, complemented by a survey of 103 users to capture real-world usability, accessibility, and security experiences. The results reveal substantial disparities between government and non-government websites, highlighting persistent issues related to navigation complexity, interaction cost, visual readability, accessibility feature adoption, and authentication mechanisms. While non-government websites generally demonstrate better usability and functional performance, accessibility support remains inconsistent across both categories. The findings underscore the need for regular accessibility audits, user-centered design practices, and policy-driven interventions to improve digital inclusivity and ensure equitable access to online services for diverse user populations.

2026-01-02T06:43:35Z Sanjida Islam Era Ishika Tarin Ime A. B. M. Alim Al Islam http://arxiv.org/abs/2512.15526v1 2025-12-17T15:27:17Z

Every day, a significant number of users visit the internet for different needs. The owners of a website generate profits from the user interaction with the contents or items of the website. A robust recommendation system can increase user interaction with a website by recommending items according to the user's unique preferences. BERT and CNN-integrated neural collaborative filtering (NCF) have been proposed for the recommendation system in this experiment. The proposed model takes inputs from the user and item profile and finds the user's interest. This model can handle numeric, categorical, and image data to extract the latent features from the inputs. The model is trained and validated on a small sample of the MovieLens dataset for 25 epochs. The same dataset has been used to train and validate a simple NCF and a BERT-based NCF model and compared with the proposed model. The proposed model outperformed those two baseline models. The obtained result for the proposed model is 0.72 recall and 0.486 Hit Ratio @ 10 for 799 users on the MovieLens dataset. This experiment concludes that considering both categorical and image data can improve the performance of a recommendation system.

2025-12-17T15:27:17Z Abdullah Al Munem Sumona Yeasmin Mohammad Rezwanul Huq http://arxiv.org/abs/2512.14336v1 2025-12-16T12:03:46Z

Scalable Vector Graphics (SVG) are central to modern web design, and the demand to animate them continues to grow as web environments become increasingly dynamic. Yet automating the animation of vector graphics remains challenging for vision-language models (VLMs) despite recent progress in code generation and motion planning. VLMs routinely mis-handle SVGs, since visually coherent parts are often fragmented into low-level shapes that offer little guidance of which elements should move together. In this paper, we introduce a framework that recovers the semantic structure required for reliable SVG animation and reveals the missing layer that current VLM systems overlook. This is achieved through a statistical aggregation of multiple weak part predictions, allowing the system to stably infer semantics from noisy predictions. By reorganizing SVGs into semantic groups, our approach enables VLMs to produce animations with far greater coherence. Our experiments demonstrate substantial gains over existing approaches, suggesting that semantic recovery is the key step that unlocks robust SVG animation and supports more interpretable interactions between VLMs and vector graphics.

2025-12-16T12:03:46Z yeolj00.github.io/personal-projects/vector-prism Jooyeol Yun Jaegul Choo http://arxiv.org/abs/2512.02850v1 2025-12-02T15:03:51Z

Modern image editors can produce identity-preserving AIGC (IP-AIGC), where the same person appears with new attire, background, or lighting. The robustness and fairness of current detectors in this regime remain unclear, especially for under-represented populations. We present what we believe is the first systematic study of IP-AIGC detection for Indian and South-Asian faces, quantifying cross-generator generalization and intra-population performance. We assemble Indian-focused training splits from FairFD and HAV-DF, and construct two held-out IP-AIGC test sets (HIDF-img-ip-genai and HIDF-vid-ip-genai) using commercial web-UI generators (Gemini and ChatGPT) with identity-preserving prompts. We evaluate two state-of-the-art detectors (AIDE and Effort) under pretrained (PT) and fine-tuned (FT) regimes and report AUC, AP, EER, and accuracy. Fine-tuning yields strong in-domain gains (for example, Effort AUC 0.739 to 0.944 on HAV-DF-test; AIDE EER 0.484 to 0.259), but consistently degrades performance on held-out IP-AIGC for Indian cohorts (for example, AIDE AUC 0.923 to 0.563 on HIDF-img-ip-genai; Effort 0.740 to 0.533), which indicates overfitting to training-generator cues. On non-IP HIDF images, PT performance remains high, which suggests a specific brittleness to identity-preserving edits rather than a generic distribution shift. Our study establishes IP-AIGC-Indian as a challenging and practically relevant scenario and motivates representation-preserving adaptation and India-aware benchmark curation to close generalization gaps in AIGC detection.

2025-12-02T15:03:51Z Vishal Dubey Pallavi Tyagi http://arxiv.org/abs/2511.19663v1 2025-11-24T19:56:28Z

Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thrived on abundant textual data, no comparable corpus exists for CUA trajectories. To address these gaps, we introduce FaraGen, a novel synthetic data generation system for multi-step web tasks. FaraGen can propose diverse tasks from frequently used websites, generate multiple solution attempts, and filter successful trajectories using multiple verifiers. It achieves high throughput, yield, and diversity for multi-step web tasks, producing verified trajectories at approximately $1 each. We use this data to train Fara-7B, a native CUA model that perceives the computer using only screenshots, executes actions via predicted coordinates, and is small enough to run on-device. We find that Fara-7B outperforms other CUA models of comparable size on benchmarks like WebVoyager, Online-Mind2Web, and WebTailBench -- our novel benchmark that better captures under-represented web tasks in pre-existing benchmarks. Furthermore, Fara-7B is competitive with much larger frontier models, illustrating key benefits of scalable data generation systems in advancing small efficient agentic models. We are making Fara-7B open-weight on Microsoft Foundry and HuggingFace, and we are releasing WebTailBench.

2025-11-24T19:56:28Z Ahmed Awadallah Yash Lara Raghav Magazine Hussein Mozannar Akshay Nambi Yash Pandya Aravind Rajeswaran Corby Rosset Alexey Taymanov Vibhav Vineet Spencer Whitehead Andrew Zhao http://arxiv.org/abs/2511.00843v1 2025-11-02T07:59:31Z

The rapid appearance of large language models (LLMs) has led to systems that turn natural-language intent into real user interfaces (UIs). Free-form code generation maximizes expressiveness but often hurts reliability, security, and design-system compliance. In contrast, fully static UIs are easy to govern but lack adaptability. We present the Portal UX Agent, a practical middle way that makes bounded generation work: an LLM plans the UI at a high level, and a deterministic renderer assembles the final interface from a vetted set of components and layout templates. The agent maps intents to a typed composition-template and component specifications-constrained by a schema. This enables auditability, reuse, and safety while preserving flexibility. We also introduce a mixed-methods evaluation framework that combines automatic checks (coverage, property fidelity, layout, accessibility, performance) with an LLM-as-a-Judge rubric to assess semantic alignment and visual polish. Experiments on multi-domain portal scenarios show that the Portal UX Agent reliably turns intent into coherent, usable UIs and performs well on compositionality and clarity. This work advances agentic UI design by combining model-driven representations, plug-and-play rendering, and structured evaluation, paving the way for controllable and trustworthy UI generation.

2025-11-02T07:59:31Z Xinsong Li Ning Jiang Jay Selvaraj http://arxiv.org/abs/2510.15842v1 2025-10-17T17:35:58Z

Academic project websites can more effectively disseminate research when they clearly present core content and enable intuitive navigation and interaction. However, current approaches such as direct Large Language Model (LLM) generation, templates, or direct HTML conversion struggle to produce layout-aware, interactive sites, and a comprehensive evaluation suite for this task has been lacking. In this paper, we introduce Paper2Web, a benchmark dataset and multi-dimensional evaluation framework for assessing academic webpage generation. It incorporates rule-based metrics like Connectivity, Completeness and human-verified LLM-as-a-Judge (covering interactivity, aesthetics, and informativeness), and PaperQuiz, which measures paper-level knowledge retention. We further present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages. The agent iteratively refines both content and layout through MCP tools that enhance emphasis, balance, and presentation quality. Our experiments show that PWAgent consistently outperforms end-to-end baselines like template-based webpages and arXiv/alphaXiv versions by a large margin while maintaining low cost, achieving the Pareto-front in academic webpage generation.

2025-10-17T17:35:58Z Under Review. Check https://github.com/YuhangChen1/Paper2All for the unified platform to streamline all academic presentation Yuhang Chen Tianpeng Lv Siyi Zhang Yixiang Yin Yao Wan Philip S. Yu Dongping Chen http://arxiv.org/abs/2510.15306v1 2025-10-17T04:37:37Z

Witnessed by the recent advancements on leveraging LLM for coding and multimodal understanding, we present WebGen-V, a new benchmark and framework for instruction-to-HTML generation that enhances both data quality and evaluation granularity. WebGen-V contributes three key innovations: (1) an unbounded and extensible agentic crawling framework that continuously collects real-world webpages and can leveraged to augment existing benchmarks; (2) a structured, section-wise data representation that integrates metadata, localized UI screenshots, and JSON-formatted text and image assets, explicit alignment between content, layout, and visual components for detailed multimodal supervision; and (3) a section-level multimodal evaluation protocol aligning text, layout, and visuals for high-granularity assessment. Experiments with state-of-the-art LLMs and ablation studies validate the effectiveness of our structured data and section-wise evaluation, as well as the contribution of each component. To the best of our knowledge, WebGen-V is the first work to enable high-granularity agentic crawling and evaluation for instruction-to-HTML generation, providing a unified pipeline from real-world data acquisition and webpage generation to structured multimodal assessment.

2025-10-17T04:37:37Z Kuang-Da Wang Zhao Wang Yotaro Shimose Wei-Yao Wang Shingo Takamatsu http://arxiv.org/abs/2510.13914v2 2026-09-07T04:26:37Z

Large language models can generate visually coherent web UIs from natural language requests, but they frequently violate Web Content Accessibility Guidelines (WCAG), excluding users with diverse needs and contexts. We address this by introducing A11yn, a post-training framework for web accessibility-aware web UI generation. A11yn converts off-the-shelf WCAG audits into a verifiable web accessibility reward, enabling accessibility alignment without data from dense human annotations. To support training and evaluation, we release UIReq-6.8K, a dataset of 6,800 diverse UI generation instructions, and RealUIReq-300, a benchmark of 300 realistic web UI generation tasks. Experimental results show that A11yn achieves the strongest web accessibility compliance among baselines, reducing the inaccessibility rate by 87.5\% and 58.1\% under two independent WCAG auditors relative to the base model. Unlike prompting-based post-hoc accessibility-correction baselines, A11yn achieves these gains in a single-pass generation setting while maintaining comparable semantic fidelity and visual quality. The code and dataset are available at https://github.com/jeffrobot/A11yn.

2025-10-15T06:42:29Z Janghan Yoon Jaegwan Cho Junhyeok Kim Jiwan Chung Jaehyun Jeon Seungwon Lim Youngjae Yu http://arxiv.org/abs/2509.25297v2 2025-10-01T17:32:51Z

Developing full-stack web applications is complex and time-intensive, demanding proficiency across diverse technologies and frameworks. Although recent advances in multimodal large language models (MLLMs) enable automated webpage generation from visual inputs, current solutions remain limited to front-end tasks and fail to deliver fully functional applications. In this work, we introduce TDDev, the first test-driven development (TDD)-enabled LLM-agent framework for end-to-end full-stack web application generation. Given a natural language description or design image, TDDev automatically derives executable test cases, generates front-end and back-end code, simulates user interactions, and iteratively refines the implementation until all requirements are satisfied. Our framework addresses key challenges in full-stack automation, including underspecified user requirements, complex interdependencies among multiple files, and the need for both functional correctness and visual fidelity. Through extensive experiments on diverse application scenarios, TDDev achieves a 14.4% improvement on overall accuracy compared to state-of-the-art baselines, demonstrating its effectiveness in producing reliable, high-quality web applications without requiring manual intervention.

2025-09-29T16:18:19Z Yuxuan Wan Tingshuo Liang Jiakai Xu Jingyu Xiao Yintong Huo Michael R. Lyu http://arxiv.org/abs/2509.24361v2 2025-09-30T07:45:11Z

Although Multimodal Large Language Models (MLLMs) have been widely applied across domains, they are still facing challenges in domain-specific tasks, such as User Interface (UI) understanding accuracy and UI generation quality. In this paper, we introduce UI-UG (a unified MLLM for UI Understanding and Generation), integrating both capabilities. For understanding tasks, we employ Supervised Fine-tuning (SFT) combined with Group Relative Policy Optimization (GRPO) to enhance fine-grained understanding on the modern complex UI data. For generation tasks, we further use Direct Preference Optimization (DPO) to make our model generate human-preferred UIs. In addition, we propose an industrially effective workflow, including the design of an LLM-friendly domain-specific language (DSL), training strategies, rendering processes, and evaluation metrics. In experiments, our model achieves state-of-the-art (SOTA) performance on understanding tasks, outperforming both larger general-purpose MLLMs and similarly-sized UI-specialized models. Our model is also on par with these larger MLLMs in UI generation performance at a fraction of the computational cost. We also demonstrate that integrating understanding and generation tasks can improve accuracy and quality for both tasks. Code and Model: https://github.com/neovateai/UI-UG

2025-09-29T06:59:09Z Hao Yang Weijie Qiu Ru Zhang Zhou Fang Ruichao Mao Xiaoyu Lin Maji Huang Zhaosong Huang Teng Guo Shuoyang Liu Hai Rao http://arxiv.org/abs/2509.22644v1 2025-09-26T17:59:51Z

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent that leverages comprehensive and multi-level visual feedback to iteratively generate and refine the website codebase. Detailed and expressive text descriptions and suggestions regarding the screenshots and GUI-agent testing of the websites are generated by a visual language model (VLM), together with scores that quantify their quality. The screenshot and GUI-agent scores are further integrated with a backtracking and select-best mechanism, enhancing the performance of the agent. Utilizing the accurate visual scores inherent in the WebGen-Agent workflow, we further introduce \textit{Step-GRPO with Screenshot and GUI-agent Feedback} to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent. By using the screenshot and GUI-agent scores at each step as the reward in Step-GRPO, we provide a dense and reliable process supervision signal, which effectively improves the model's website-generation ability. On the WebGen-Bench dataset, WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system. Additionally, our Step-GRPO training approach increases the accuracy of Qwen2.5-Coder-7B-Instruct from 38.9% to 45.4% and raises the appearance score from 3.4 to 3.7.

2025-09-26T17:59:51Z Zimu Lu Houxing Ren Yunqiao Yang Ke Wang Zhuofan Zong Junting Pan Mingjie Zhan Hongsheng Li http://arxiv.org/abs/2509.21733v1 2025-09-26T01:02:00Z

Developing and testing user interfaces (UIs) and training AI agents to interact with them are challenging due to the dynamic and diverse nature of real-world mobile environments. Existing methods often rely on cumbersome physical devices or limited static analysis of screenshots, which hinders scalable testing and the development of intelligent UI agents. We introduce UISim, a novel image-based UI simulator that offers a dynamic and interactive platform for exploring mobile phone environments purely from screen images. Our system employs a two-stage method: given an initial phone screen image and a user action, it first predicts the abstract layout of the next UI state, then synthesizes a new, visually consistent image based on this predicted layout. This approach enables the realistic simulation of UI transitions. UISim provides immediate practical benefits for UI testing, rapid prototyping, and synthetic data generation. Furthermore, its interactive capabilities pave the way for advanced applications, such as UI navigation task planning for AI agents. Our experimental results show that UISim outperforms end-to-end UI generation baselines in generating realistic and coherent subsequent UI states, highlighting its fidelity and potential to streamline UI development and enhance AI agent training.

2025-09-26T01:02:00Z Jiannan Xiang Yun Zhu Lei Shu Maria Wang Lijun Yu Gabriel Barcik James Lyon Srinivas Sunkara Jindong Chen http://arxiv.org/abs/2509.16779v2 2026-02-16T19:19:25Z

Despite being trained on vast amounts of data, most LLMs are unable to reliably generate well-designed UIs. Designer feedback is essential to improving performance on UI generation; however, we find that existing RLHF methods based on ratings or rankings are not well-aligned with with designers' workflows and ignore the rich rationale used to critique and improve UI designs. In this paper, we investigate several approaches for designers to give feedback to UI generation models, using familiar interactions such as commenting, sketching and direct manipulation. We first perform an evaluation with 21 designers where they gave feedback using these interactions, which resulted in 1500 design annotations. We then use this data to finetune a series of LLMs to generate higher quality UIs. Finally, we evaluate these models with human judges, and we find that our designer-aligned approaches outperform models trained with traditional ranking feedback and all tested baselines, including GPT-5.

2025-09-20T19:02:53Z Version accepted to CHI 2026 Jason Wu Amanda Swearngin Arun Krishna Vajjala Alan Leung Jeffrey Nichols Titus Barik 10.1145/3772318.3791567 http://arxiv.org/abs/2509.10402v2 2026-08-28T20:55:17Z

Large Language Models (LLMs) are increasingly used by developers for conversational coding assistance, including code generation, technical questions, and iterative problem solving. However, limited empirical evidence exists on the topics developers discuss with LLMs, how interaction patterns vary across tasks, and how the quality of generated code changes across conversational turns. To address this, we construct CodeChat, a large-scale dataset derived from WildChat. CodeChat contains 587,568 real-world developer-LLM conversations and 1.7 million code snippets across more than 20 programming languages. We identify the topics developers raise and examine how their engagement varies across topics. We then assess the quality of generated code across five programming languages (i.e., Python, JavaScript, C++, Java, and C#) and analyze how quality issues evolve across conversational turns. We find that developers most frequently seek help with web design (9.6% of conversations) and machine learning (8.7%), and that conversations often grow long because developers repeatedly shift use cases. LLM-generated code exhibits prevalent, language-specific issues whose prevalence does not consistently decrease in interactions lasting at least five turns. Among successful syntax-error resolutions, prompts that explicitly identify the error and request a fix are the most frequently observed. Our findings suggest that conversational assistants should track evolving developer intent and monitor code quality across turns.

2025-09-12T16:52:49Z Suzhen Zhong Ying Zou Bram Adams http://arxiv.org/abs/2508.20410v3 2025-09-03T23:48:21Z

AI text-to-app tools promise high quality applications and websites in minutes, yet no public benchmark rigorously verifies those claims. We introduce UI-Bench, the first large-scale benchmark that evaluates visual excellence across competing AI text-to-app tools through expert pairwise comparison. Spanning 10 tools, 30 prompts, 300 generated sites, and 4,000+ expert judgments, UI-Bench ranks systems with a TrueSkill-derived model that yields calibrated confidence intervals. UI-Bench establishes a reproducible standard for advancing AI-driven web design. We release (i) the complete prompt set, (ii) an open-source evaluation framework, and (iii) a public leaderboard. The generated sites rated by participants will be released soon. View the UI-Bench leaderboard at https://uibench.ai/leaderboard.

2025-08-28T04:20:00Z Sam Jung Agustin Garcinuno Spencer Mateega http://arxiv.org/abs/2508.09171v1 2025-08-06T23:02:36Z

Current AI agents create significant barriers for users by requiring extensive processing to understand web pages, making AI-assisted web interaction slow and expensive. This paper introduces webMCP (Web Machine Context & Procedure), a client-side standard that embeds structured interaction metadata directly into web pages, enabling more efficient human-AI collaboration on existing websites. webMCP transforms how AI agents understand web interfaces by providing explicit mappings between page elements and user actions. Instead of processing entire HTML documents, agents can access pre-structured interaction data, dramatically reducing computational overhead while maintaining task accuracy. A comprehensive evaluation across 1,890 real API calls spanning online shopping, authentication, and content management scenarios demonstrates webMCP reduces processing requirements by 67.6% while maintaining 97.9% task success rates compared to 98.8% for traditional approaches. Users experience significantly lower costs (34-63% reduction) and faster response times across diverse web interactions. Statistical analysis confirms these improvements are highly significant across multiple AI models. An independent WordPress deployment study validates practical applicability, showing consistent improvements across real-world content management workflows. webMCP requires no server-side modifications, making it deployable across millions of existing websites without technical barriers. These results establish webMCP as a viable solution for making AI web assistance more accessible and sustainable, addressing the critical gap between user interaction needs and AI computational requirements in production environments.

2025-08-06T23:02:36Z D. Perera http://arxiv.org/abs/2508.03560v1 2025-08-05T15:28:48Z

Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and functional implementation. While recent Multimodal Large Language Models (MLLMs) have shown significant potential in design-to-code tasks, they often fail to accurately preserve the layout during code generation. To this end, we draw inspiration from the Chain-of-Thought (CoT) reasoning in human cognition and propose LaTCoder, a novel approach that enhances layout preservation in webpage design during code generation with Layout-as-Thought (LaT). Specifically, we first introduce a simple yet efficient algorithm to divide the webpage design into image blocks. Next, we prompt MLLMs using a CoTbased approach to generate code for each block. Finally, we apply two assembly strategies-absolute positioning and an MLLM-based method-followed by dynamic selection to determine the optimal output. We evaluate the effectiveness of LaTCoder using multiple backbone MLLMs (i.e., DeepSeek-VL2, Gemini, and GPT-4o) on both a public benchmark and a newly introduced, more challenging benchmark (CC-HARD) that features complex layouts. The experimental results on automatic metrics demonstrate significant improvements. Specifically, TreeBLEU scores increased by 66.67% and MAE decreased by 38% when using DeepSeek-VL2, compared to direct prompting. Moreover, the human preference evaluation results indicate that annotators favor the webpages generated by LaTCoder in over 60% of cases, providing strong evidence of the effectiveness of our method.

2025-08-05T15:28:48Z KDD 2025 v2 Yi Gui Zhen Li Zhongyi Zhang Guohao Wang Tianpeng Lv Gaoyang Jiang Yi Liu Dongping Chen Yao Wan Hongyu Zhang Wenbin Jiang Xuanhua Shi Hai Jin 10.1145/3711896.3737016 http://arxiv.org/abs/2507.22827v2 2025-10-20T14:13:43Z

Automating the transformation of user interface (UI) designs into front-end code holds significant promise for accelerating software development and democratizing design workflows. While multimodal large language models (MLLMs) can translate images to code, they often fail on complex UIs, struggling to unify visual perception, layout planning, and code synthesis within a single monolithic model, which leads to frequent perception and planning errors. To address this, we propose ScreenCoder, a modular multi-agent framework that decomposes the task into three interpretable stages: grounding, planning, and generation. By assigning these distinct responsibilities to specialized agents, our framework achieves significantly higher robustness and fidelity than end-to-end approaches. Furthermore, ScreenCoder serves as a scalable data engine, enabling us to generate high-quality image-code pairs. We use this data to fine-tune open-source MLLM via a dual-stage pipeline of supervised fine-tuning and reinforcement learning, demonstrating substantial gains in its UI generation capabilities. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in layout accuracy, structural coherence, and code correctness. Our code is made publicly available at https://github.com/leigest519/ScreenCoder.

2025-07-30T16:41:21Z ScreenCoder-v2 Yilei Jiang Yaozhi Zheng Yuxuan Wan Jiaming Han Qunzhong Wang Michael R. Lyu Xiangyu Yue http://arxiv.org/abs/2506.07818v1 2025-06-09T14:46:02Z

With the rapid advancement of Generative AI technology, Multimodal Large Language Models(MLLMs) have the potential to act as AI software engineers capable of executing complex web application development. Considering that the model requires a confluence of multidimensional sub-capabilities to address the challenges of various development phases, constructing a multi-view evaluation framework is crucial for accurately guiding the enhancement of development efficiency. However, existing benchmarks usually fail to provide an assessment of sub-capabilities and focus solely on webpage generation outcomes. In this work, we draw inspiration from the principles of software engineering and further propose WebUIBench, a benchmark systematically designed to evaluate MLLMs in four key areas: WebUI Perception, HTML Programming,WebUI-HTML Understanding, and WebUI-to-Code. WebUIBench comprises 21K high-quality question-answer pairs derived from over 0.7K real-world websites. The extensive evaluation of 29 mainstream MLLMs uncovers the skill characteristics and various weakness that models encountered during the development process.

2025-06-09T14:46:02Z Zhiyu Lin Zhengda Zhou Zhiyuan Zhao Tianrui Wan Yilun Ma Junyu Gao Xuelong Li http://arxiv.org/abs/2505.09904v2 2025-05-23T08:34:36Z

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. The core idea of UICopilot is to decompose the generation process into two stages: first, generating the coarse-grained HTML hierarchical structure, followed by the generation of fine-grained code. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V.

2025-05-15T02:09:54Z WWW' 2025 Yi Gui Zhen Li Zhongyi Zhang Yao Wan Dongping Chen Hongyu Zhang Yi Su Bohua Chen Xing Zhou Wenbin Jiang Xiangliang Zhang http://arxiv.org/abs/2505.04670v2 2025-06-04T12:57:19Z

With the rise of AI-based code generation, customizing existing code out of natural language instructions to modify visual results -such as figures or images -has become possible, promising to reduce the need for deep programming expertise. However, even experienced developers can struggle with this task, as it requires identifying relevant code regions (feature location), generating valid code variants, and ensuring the modifications reliably align with user intent. In this paper, we introduce vTikZ, the first benchmark designed to evaluate the ability of Large Language Models (LLMs) to customize code while preserving coherent visual outcomes. Our benchmark consists of carefully curated vTikZ editing scenarios, parameterized ground truths, and a reviewing tool that leverages visual feedback to assess correctness. Empirical evaluation with stateof-the-art LLMs shows that existing solutions struggle to reliably modify code in alignment with visual intent, highlighting a gap in current AI-assisted code editing approaches. We argue that vTikZ opens new research directions for integrating LLMs with visual feedback mechanisms to improve code customization tasks in various domains beyond TikZ, including image processing, art creation, Web design, and 3D modeling.

2025-05-07T08:26:54Z EASE 2025 - Evaluation and Assessment in Software Engineering, Jun 2025, Istanbul, Turkey. pp.1-10 Charly Reux DiverSe Mathieu Acher DiverSe Djamel Eddine Khelladi DiverSe Olivier Barais DiverSe Clément Quinton SPIRALS http://arxiv.org/abs/2505.03733v2 2025-08-11T07:13:00Z

LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multi-file website codebases from scratch. It contains diverse instructions for website generation, created through the combined efforts of human annotators and GPT-4o. These instructions span three major categories and thirteen minor categories, encompassing nearly all important types of web applications. To assess the quality of the generated websites, we use GPT-4o to generate test cases targeting each functionality described in the instructions, and then manually filter, adjust, and organize them to ensure accuracy, resulting in 647 test cases. Each test case specifies an operation to be performed on the website and the expected result after the operation. To automate testing and improve reproducibility, we employ a powerful web-navigation agent to execute tests on the generated websites and determine whether the observed responses align with the expected results. We evaluate three high-performance code-agent frameworks, Bolt.diy, OpenHands, and Aider, using multiple proprietary and open-source LLMs as engines. The best-performing combination, Bolt.diy powered by DeepSeek-R1, achieves only 27.8\% accuracy on the test cases, highlighting the challenging nature of our benchmark. Additionally, we construct WebGen-Instruct, a training set consisting of 6,667 website-generation instructions. Training Qwen2.5-Coder-32B-Instruct on Bolt.diy trajectories generated from a subset of this training set achieves an accuracy of 38.2\%, surpassing the performance of the best proprietary model.

2025-05-06T17:59:15Z Zimu Lu Yunqiao Yang Houxing Ren Haotian Hou Han Xiao Ke Wang Weikang Shi Aojun Zhou Mingjie Zhan Hongsheng Li http://arxiv.org/abs/2505.01451v2 2025-05-07T07:11:49Z

Modern Search Engine Results Pages (SERPs) present complex layouts where multiple elements compete for visibility. Attention modelling is crucial for optimising web design and computational advertising, whereas attention metrics can inform ad placement and revenue strategies. We introduce AdSight, a method leveraging mouse cursor trajectories to quantify in a scalable and accurate manner user attention in multi-slot environments like SERPs. AdSight uses a novel Transformer-based sequence-to-sequence architecture where the encoder processes cursor trajectory embeddings, and the decoder incorporates slot-specific features, enabling robust attention prediction across various SERP layouts. We evaluate our approach on two Machine Learning tasks: (1) regression, to predict fixation times and counts; and (2) classification, to determine some slot types were noticed. Our findings demonstrate the model's ability to predict attention with unprecedented precision, offering actionable insights for researchers and practitioners.

2025-04-30T08:51:26Z Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval Mario Villaizán-Vallelado Matteo Salvatori Kayhan Latifzadeh Antonio Penta Luis A. Leiva Ioannis Arapakis 10.1145/3726302.3729891 http://arxiv.org/abs/2504.18729v1 2025-04-25T22:48:10Z

The Design2Code problem, which involves converting digital designs into functional source code, is a significant challenge in software development due to its complexity and time-consuming nature. Traditional approaches often struggle with accurately interpreting the intricate visual details and structural relationships inherent in webpage designs, leading to limitations in automation and efficiency. In this paper, we propose a novel method that leverages multimodal graph representation learning to address these challenges. By integrating both visual and structural information from design sketches, our approach enhances the accuracy and efficiency of code generation, particularly in producing semantically correct and structurally sound HTML code. We present a comprehensive evaluation of our method, demonstrating significant improvements in both accuracy and efficiency compared to existing techniques. Extensive evaluation demonstrates significant improvements of multimodal graph learning over existing techniques, highlighting the potential of our method to revolutionize design-to-code automation. Code available at https://github.com/HySonLab/Design2Code

2025-04-25T22:48:10Z Tung D. Vu Chung Hoang Truong-Son Hy http://arxiv.org/abs/2504.09407v3 2025-09-19T17:52:50Z

Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the usability testing study design itself? Recent advances in Large Language Model-simulated Agent (LLM Agent) research inspired us to design UXAgent to support UX researchers in evaluating and iterating their study design before they conduct the real human-subject study. Our system features a Persona Generator module, an LLM Agent module, and a Universal Browser Connector module to automatically generate thousands of simulated users and to interactively test the target website. The system also provides a Result Viewer Interface so that the UX researchers can easily review and analyze the generated qualitative (e.g., agents' post-study surveys) and quantitative data (e.g., agents' interaction logs), or even interview agents directly. Through a heuristic evaluation with 16 UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent usage in UX studies.

2025-04-13T02:34:22Z Yuxuan Lu Bingsheng Yao Hansu Gu Jing Huang Jessie Wang Yang Li Jiri Gesi Qi He Toby Jia-Jun Li Dakuo Wang http://arxiv.org/abs/2503.04084v1 2025-03-06T04:46:16Z

Unlike static and rigid user interfaces, generative and malleable user interfaces offer the potential to respond to diverse users' goals and tasks. However, current approaches primarily rely on generating code, making it difficult for end-users to iteratively tailor the generated interface to their evolving needs. We propose employing task-driven data models-representing the essential information entities, relationships, and data within information tasks-as the foundation for UI generation. We leverage AI to interpret users' prompts and generate the data models that describe users' intended tasks, and by mapping the data models with UI specifications, we can create generative user interfaces. End-users can easily modify and extend the interfaces via natural language and direct manipulation, with these interactions translated into changes in the underlying model. The technical evaluation of our approach and user evaluation of the developed system demonstrate the feasibility and effectiveness of the proposed generative and malleable UIs.

2025-03-06T04:46:16Z Yining Cao Peiling Jiang Haijun Xia http://arxiv.org/abs/2502.18701v2 2025-04-22T02:25:56Z

Online interactions and e-commerce are commonplace among BLV users. Despite the implementation of web accessibility standards, many e-commerce platforms continue to present challenges to screen reader users, particularly in areas like webpage navigation and information retrieval. We investigate the difficulties encountered by screen reader users during online shopping experiences. We conducted a formative study with BLV users and designed a web browser plugin that uses GenAI to restructure webpage content in real time. Our approach improved the header hierarchy and provided correct labeling for essential information. We evaluated the effectiveness of this solution using an automated accessibility tool and through user interviews. Our results show that the revised webpages generated by our system offer significant improvements over the original webpages regarding screen reader navigation experience. Based on our findings, we discuss its potential usage as both a user and developer tool that can significantly enhance screen reader accessibility of webpages.

2025-02-25T23:28:30Z Yaman Yu Bektur Ryskeldiev Ayaka Tsutsui Matthew Gillingham Yang Wang http://arxiv.org/abs/2502.12614v1 2025-02-18T07:53:26Z

Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multi-modal, few-shot and zero-shot settings.\footnote{https://github.com/Lu-Yang666/LDNet}

2025-02-18T07:53:26Z Accepted to NAACL-main 2025 Lu Yang Jiajia Li En Ci Lefei Zhang Zuchao Li Ping Wang http://arxiv.org/abs/2502.12561v3 2025-04-05T01:55:09Z

Usability testing is a fundamental yet challenging (e.g., inflexible to iterate the study design flaws and hard to recruit study participants) research method for user experience (UX) researchers to evaluate a web design. Recent advances in Large Language Model-simulated Agent (LLM-Agent) research inspired us to design UXAgent to support UX researchers in evaluating and reiterating their usability testing study design before they conduct the real human subject study. Our system features an LLM-Agent module and a universal browser connector module so that UX researchers can automatically generate thousands of simulated users to test the target website. The results are shown in qualitative (e.g., interviewing how an agent thinks ), quantitative (e.g., # of actions), and video recording formats for UX researchers to analyze. Through a heuristic user evaluation with five UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent-assisted UX study.

2025-02-18T05:55:18Z Yuxuan Lu Bingsheng Yao Hansu Gu Jing Huang Jessie Wang Yang Li Jiri Gesi Qi He Toby Jia-Jun Li Dakuo Wang 10.1145/3706599.3719729 http://arxiv.org/abs/2412.20071v3 2025-10-29T05:00:04Z

In automated UI design generation, a key challenge is the lack of support for iterative processes, as most systems focus solely on end-to-end output. This stems from limited capabilities in interpreting design intent and a lack of transparency for refining intermediate results. To better understand these challenges, we conducted a formative study that identified concrete and actionable requirements for supporting iterative design with Generative Tools. Guided by these findings, we propose PrototypeFlow, a human-centered system for automated UI generation that leverages multi-modal inputs and models. PrototypeFlow takes natural language descriptions and layout preferences as input to generate the high-fidelity UI design. At its core is a theme design module that clarifies implicit design intent through prompt enhancement and orchestrates sub-modules for component-level generation. Designers retain full control over inputs, intermediate results, and final prototypes, enabling flexible and targeted refinement by steering generation and directly editing outputs. Our experiments and user studies confirmed the effectiveness and usefulness of our proposed PrototypeFlow.

2024-12-28T07:54:00Z ACM Transactions on Computer-Human Interaction Mingyue Yuan Jieshan Chen Yongquan Hu Sidong Feng Mulong Xie Gelareh Mohammadi Zhenchang Xing Aaron Quigley 10.1145/3773035