Showing 1–25 of 79,267 results for abstract: "tool output" OR "context compression" OR "token efficiency" agent

Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Authors: Liming Lu, Xianzheng Ma, Wenkun He, Guanqi Zhan, Yilin Zhao, Junyu Chen, Mengyao Xu, Jiaojiao Fan, Wenhang Ge, Yuchao Gu, Yunze Liu, Boyi Li, Zhen Dong, Victor Prisacariu, Ming-Yu Liu, Song Han, Han Cai

Abstract: …To improve this representation, we construct PhysCapBench, which decomposes physical processes into atomic assertions and evaluates captions using recall and precision. An agentic loop iteratively analyzes assertion-level errors and refines the instruction used to produce physical captions. Physis-Lang further converts model deficiencies into textual descri… ▽ More Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approaches commonly assume that natural language is insufficient to represent the physical knowledge required for reliable generation, and therefore introduce additional visual, latent, numerical, or planning-based signals. We revisit this assumption and introduce Physis-Lang, a self-evolving framework that treats physical language as a shared and optimizable representation across data curation, model training, and video generation. Physis-Lang represents physical processes through language that describes their relevant entities, causes, interactions, governing principles, temporal evolution, and effects. To improve this representation, we construct PhysCapBench, which decomposes physical processes into atomic assertions and evaluates captions using recall and precision. An agentic loop iteratively analyzes assertion-level errors and refines the instruction used to produce physical captions. Physis-Lang further converts model deficiencies into textual descriptions and uses language-guided retrieval to identify visually diverse videos that cover missing physical processes. Experiments on four widely used physical video benchmarks with Wan and Cosmos backbones demonstrate consistent improvements in physical plausibility. Notably, starting from open-source Cosmos3-Nano backbones, our Physis-Lang-enhanced models surpass the leading proprietary Veo 3.1 model. △ Less

Submitted 30 September, 2026; originally announced September 2026.

AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents

Authors: Jiahao Zhang, Yeying Fan, Moitreya Chatterjee, Suhas Lohit, Bernhard Egger, Tim K. Marks, Anoop Cherian, Stephen Gould

Abstract: The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general-purpose agents assemble objects through visual interaction without additional assembly-specific fine-tuning? To investigate this question, we introduce AssemblyWorld, an interactive 3D environment in which… ▽ More The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general-purpose agents assemble objects through visual interaction without additional assembly-specific fine-tuning? To investigate this question, we introduce AssemblyWorld, an interactive 3D environment in which agents inspect rendered views and manipulate supplied rigid parts, guided by images or assembly manuals when available. Agents perceive part geometry through 2D views rather than direct access to mesh vertices or faces, while their resulting assemblies are evaluated geometrically. Building on this environment, we construct AssemblyWorldBench, comprising 100 assembly tasks across 80 objects spanning furniture, industrial assembly, and fracture reassembly. Evaluating eight agent systems reveals substantial differences in their capabilities. The strongest system achieves 80.9% part accuracy but 59.4% complete-assembly success. The evaluated open-source systems lag substantially behind their stronger closed-source peers in both execution reliability and assembly accuracy. Analyses of visual references, interaction trajectories, and failures show how agents revise assemblies while leaving residual positioning errors. AssemblyWorld provides a common setting for both assessing the capabilities of interactive assembly agents and characterizing the gap between approximate structure recovery and precise reconstruction. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: 24 pages, 11 figures. Project page: https://assemblyworld.github.io

Turbo Harness: Instance-Adaptive Harness Optimization

Authors: Tunyu Zhang, Hao Wang, Kai Xu, Dimitris N. Metaxas

Abstract: Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances. However, a harness that works well on average may not be optimal for every instance. We introduce Turbo Harness, a fram… ▽ More Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances. However, a harness that works well on average may not be optimal for every instance. We introduce Turbo Harness, a framework that can adapt a globally optimized harness to each instance by reusing information generated during the original optimization process. Specifically, Turbo Harness recycles artifacts produced during a completed global harness optimization run, and summarizes them into a structured playbook. We train a harness editor to leverage this prior optimization experience to generate instance-specific patches to the global harness. At inference time, the editor uses the instance and the playbook to construct a tailored harness in which the execution model operates. Through numerical experiments, we show that Turbo Harness consistently outperforms existing harness optimization baselines across seven benchmarks spanning interactive agent tasks, software engineering, and long-horizon terminal tasks. △ Less

Submitted 30 September, 2026; originally announced September 2026.

WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents

Authors: Ziyan Jiang, Jingbo Yang, Jiabao Ji, Yujian Liu, Qiucheng Wu, Tommi Jaakkola, Yang Zhang, Shiyu Chang

Abstract: …and efficiently; and visual reasoning, to understand the environment and identify anomalies from multimodal observations. It remains largely unexplored whether multimodal agents can effectively couple these two capabilities, using visual reasoning to identify potential anomalies while taking actions to validate them. In this paper, we introduce WorldAuditBen… ▽ More As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, traversable walls, or objects inconsistent with the surrounding scene. Multimodal AI systems, including vision-language models (VLMs) and vision-language-action models (VLAs), have shown potential for automating this task. However, 3D world auditing is complex, requiring the close coupling of two distinct capabilities: action, to navigate the 3D world and search for anomalies systematically and efficiently; and visual reasoning, to understand the environment and identify anomalies from multimodal observations. It remains largely unexplored whether multimodal agents can effectively couple these two capabilities, using visual reasoning to identify potential anomalies while taking actions to validate them. In this paper, we introduce WorldAuditBench, a benchmark for 3D world auditing comprising 213 anomaly tasks across 13 environments built with Unreal Engine 5 and Three.js, spanning five anomaly families. We evaluate five frontier models under a fixed exploration budget using two auditing paradigms: VLA-based exploration followed by VLM-based anomaly identification, and an end-to-end VLM agent in which visual reasoning directly guides action selection. Across the evaluated models and two paradigms, success rates range from 6.6% to 42.3%, substantially below human performance (83.4%). Through the task of world auditing, WorldAuditBench provides a testbed for studying how multimodal agents couple action and visual reasoning in interactive 3D environments, while highlighting current limitations in their ability to gather and interpret evidence during exploration. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Cogentic: Multi-Agent Orchestration for Automated Proof Discovery

Authors: Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Grigoris Velegkas, Di Wang

Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retainin… ▽ More We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addresses these challenges through an iterative prove--verify loop in which an orchestrator allocates a population of independent provers across distinct proof directions, subjects their output to adversarial verification by several specialized components, and promotes confirmed intermediate results into a persistent verified ledger that later rounds build on. The harness is designed to be able to solve research-level math and theoretical computer science problems. Using Gemini as the base model, Cogentic produced novel results on five open problems across online learning, auction theory, and mechanism design. Each result was independently verified by domain experts and is developed in full in companion papers. We list these results, and new ones as they are verified, at https://sites.google.com/view/cogentic . △ Less

Submitted 30 September, 2026; originally announced September 2026.

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

Authors: Kirill Brilliantov, Alejandro Hernández-Cano, Emmanuel Abbé

Abstract: Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern MLE… ▽ More Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern MLE agents are deployed on top of increasingly elaborate machinery: multi-agent orchestrators, dedicated retrieval subagents, and more. While such harnesses expand, the use of more primitive but improved coding agents - where LLMs have direct access to the execution environment through read, write, and bash primitives - has received little attention in the field. In this paper we find that, under an equal time budget and the same frontier LLM backbone, open-source state-of-the-art harnesses provide no advantages over a single session of a minimal-harness coding agent baseline, pointing to the backbone as the primary driver for performance. Via a series of large-scale systematic ablation studies, we argue that the machinery layers become redundant in the coding agent setting. We conclude that the effort spent elaborating hand-crafted harnesses around strong models yields poor returns for current MLE benchmarks. △ Less

Submitted 30 September, 2026; originally announced September 2026.

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

Authors: Yinghui He, Yapei Chang, Khushi Bhardwaj, Daniele Molinari, Tugrul Konuk, Jan Kautz, Ali Hatamizadeh

Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-turn interaction, an incorrect action changes the states the student encounters later, so errors compound across turns. In preliminary experiments across three Qwen3 models (8B to 235B), w… ▽ More On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-turn interaction, an incorrect action changes the states the student encounters later, so errors compound across turns. In preliminary experiments across three Qwen3 models (8B to 235B), we find that more than half of the failed rollouts contain a pivotal mistake, an action that moves the agent farther from completing the task, and this mistake typically occurs early. These pivotal mistakes often remain recoverable: guiding the model for only a few turns after the pivotal turn can restore task success. We therefore propose PivotOPD, an on-policy distillation framework that jointly trains the student to prevent pivotal mistakes and to recover from the states they create. At each pivotal mistake, a teacher model provides a gold action and then names a recovery action at each of the next few turns. Preventive distillation uses the gold action with reverse KL to steer the student away from the pivotal mistake, while recovery distillation uses the recovery actions with forward KL to transfer recovery behaviors that the student rarely samples. Against 13 baselines on ALFWorld, WebShop, and Search-based QA, PivotOPD achieves the strongest average performance for both Qwen3-1.7B and Qwen3-8B students, improving over the strongest baseline on ALFWorld by +5.5% with the 1.7B student. The gains also transfer to another model family on the software engineering domain, where PivotOPD raises the resolve rate of a Nemotron-3.5 student on SWE-Bench Verified by +3.2%. Project page: https://research.nvidia.com/labs/lpr/pivotopd/ △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: PivotOPD technical report; Project page: https://research.nvidia.com/labs/lpr/pivotopd/

cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents

Authors: Pranjal Aggarwal, Lawrence Keunho Jang, Sean Welleck, Daniel Fried, Ruslan Salakhutdinov, Jing Yu Koh

Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchmarks, including difficult long-horizon tasks. Their capabilities are undoubtedly impressive, however, a key barrier to the widespread adoption and deployment of CUAs remains their speed and c… ▽ More Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchmarks, including difficult long-horizon tasks. Their capabilities are undoubtedly impressive, however, a key barrier to the widespread adoption and deployment of CUAs remains their speed and cost. Progress towards faster yet capable CUAs requires reliable evaluation of their speed, but many CUA benchmarks currently face a reproducibility crisis. Benchmarks are based on complex infrastructure with varying machine and container configurations that confound the evaluation of the execution speed of CUAs. Towards addressing this gap, we propose cua-speedrun, which introduces standardized infrastructure and task sets, with a focus on evaluating the speed and efficiency of CUAs. cua-speedrun uses a uniform virtual machine setup and execution pipeline, along with a common agent interface that enables single-agent implementations to operate seamlessly across different benchmarks. Across four different CUA benchmarks, we evaluate how reasoning effort, agent harnesses, and environment latency affect performance, speed, and cost. We find no single model family is optimal for all three; none of the open-weight models are on the frontier, and also, unintuitively, for some models increasing the reasoning effort can speed up task completion, while faster environment input-output can slow down overall task completion time. We also demonstrate that we can effectively reduce the evaluation task set of most CUA benchmarks without degrading overall statistical power, allowing for more efficient benchmarking and comparison. We believe cua-speedrun will enable structured progress towards fast, efficient CUAs, unlocking new real-world use cases and applications. All code, infrastructure, and analysis are available at https://cuaspeedrun.com. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Skill-Based AI Agents for Power-System Studies

Authors: Pavel Etingov, Shuchismita Biswas

Abstract: This paper describes a skill-based agentic framework for power-system studies using Model Context Protocol (MCP)-connected engineering tools. A custom MCP server was developed to expose Siemens PTI PSSE functions for power-flow analysis, dynamic simulation, result extraction, and model-validation workflows. Two implementation pathways built on a programmable… ▽ More This paper describes a skill-based agentic framework for power-system studies using Model Context Protocol (MCP)-connected engineering tools. A custom MCP server was developed to expose Siemens PTI PSSE functions for power-flow analysis, dynamic simulation, result extraction, and model-validation workflows. Two implementation pathways built on a programmable OpenAI Agents software development kit (SDK) and a Claude Code command-line interface (CLI) were evaluated, both using reusable skills, subagents, MCP tools, data-repository connections, and local shell/Python execution. Both frontier-model-based implementations successfully executed representative study tasks. Success was evaluated based on task completion, output accuracy, and the need for human expert interventions. Results based on public datasets show that agentic systems can greatly accelerate power system dynamic simulation process for transmission planning studies leveraging industry-grade simulation platforms. This points toward a shift in transmission planning practice, where agentic systems could handle routine simulation setup and result extraction, allowing engineers to focus expert judgment on scenario design and interpretation rather than tool operation. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: submitted to 2027 IEEE PES Grid Edge Technologies Conference & Exposition

Belief-Aware Multi-Agent Path Finding under Map Uncertainty

Authors: Viraj Parimi, Shao-Hung Chan, Han Zhang, Jingkai Chen, Brian Williams

Abstract: Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple… ▽ More Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in advance, but real-world environments can change unexpectedly due to fallen objects, spills, or other local disturbances. When such changes are spatially correlated, an observation can inform traversability estimates beyond the observed location. Prior approaches address uncertainty in traversability through contingent plans or replanning based on direct observations, but do not leverage this spatial dependence to infer the traversability of nearby unobserved locations. As a result, they cannot use one observation to anticipate nearby unobserved obstacles that may cause costly rerouting later. We focus on Belief-Aware MAPF, where map discrepancies are fixed during execution but initially unknown, and observations can be informative beyond the observed location. We propose Multi-Agent Gaussian belief Inference for Coordination (MAGIC), a framework that updates a shared belief about traversability online based on agents' observations. MAGIC uses a Gaussian Markov Random Field and Gaussian Belief Propagation to approximately infer traversability and construct detour-aware costs for standard MAPF planners. Our experiments on MAPF benchmarks show that MAGIC reduces the executed sum of costs compared to existing approaches on 96.3% of instances, across several planner families and teams of up to 800 agents, demonstrating its applicability to large-scale MAPF problems. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: Under review

Two-sided Market Design Meets Autobidding

Authors: Yang Cai, Christopher Liaw, Aranyak Mehta, Xizhi Tan, Mingfei Zhao

Abstract: …gains from trade (LGFT) in the prior-free setting, broad classes of utility-truthful, budget-balanced mechanisms have unbounded Price of Anarchy (PoA) once value-maximizing agents are present, even in double-auction environments. We then give two positive results. In the prior-free repeated double-auction setting, McAfee's Trade Reduction mechanism has… ▽ More Autobidding has become a dominant paradigm in online advertising by enabling advertisers to set high-level goals while algorithms handle real-time bid optimization. A prominent example is the Return-on-Spend (RoS) value maximizer, which maximizes total value subject to an aggregate value-per-spend constraint. While most work on mechanism design for autobidders focuses on one-sided markets, many real-world platforms involve strategic behavior on both sides. We initiate the study of two-sided markets with autobidders. We first establish a stark negative result: for the challenging objective of liquid gains from trade (LGFT) in the prior-free setting, broad classes of utility-truthful, budget-balanced mechanisms have unbounded Price of Anarchy (PoA) once value-maximizing agents are present, even in double-auction environments. We then give two positive results. In the prior-free repeated double-auction setting, McAfee's Trade Reduction mechanism has unbounded PoA for LGFT but achieves constant PoA for liquid welfare under RoS bidding, showing that off-the-shelf mechanisms retain meaningful welfare guarantees. With distributional information regarding the private costs and values, we design a two-sided mechanism that is incentive compatible for each agent under its corresponding objective, individually rational, ex-ante weakly budget balanced, and achieves first-best liquid welfare, equivalently optimal LGFT, whenever at least one side of the market consists of RoS value maximizers. This result applies to matching markets with general downward-closed feasibility constraints. It contrasts sharply with the Myerson--Satterthwaite impossibility theorem~\citep{MS83}, which rules out first-best efficiency with incentive compatibility, individual rationality, and budget balance even in bilateral trade when both the buyer and the seller are quasi-linear utility maximizers. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: To appear in the 22nd Conference on Web and Internet Economics (WINE2026)

ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents

Authors: Yong Du, Tongbo Chen, Zhengxi Lu, Yizhou Liu, Bofan Chen, Tao Jiang, Wenhao Xu, Yongliang Shen

Abstract: Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it… ▽ More Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it to CUA online training presents two challenges: fixed guidance may become misaligned with the student's current state, and guidance-induced probability shifts may conflict with step-level correctness. We introduce ComputerSD, an online self-distillation method for CUAs that converts real-time feedback from executed GUI transitions into guidance for policy learning. A fine-tuned GUI analyzer produces guidance and a step-level value score after each action; the guidance provides privileged context, while the score regulates the resulting OPSD signals. ComputerSD jointly optimizes token-level OPSD and trajectory-level GRPO in a fully asynchronous training framework. On OSWorld-Verified, ComputerSD outperforms outcome-only GRPO by 1.9 and 4.1 percentage points on the general-purpose Qwen3-VL-8B-Thinking and specialized EvoCUA-8B backbones, respectively. Evaluation in out-of-distribution settings further supports the generalizability of ComputerSD. These results demonstrate the effectiveness of learning from real-time feedback through online self-distillation for CUAs. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: https://github.com/ZJU-REAL/ComputerSD

Herschel: Continuous Optimization of Production LLM Inference through On-Demand Profiling

Authors: Luping Wang, Weigao Chen, Yifei Wu, Yonghe Zhang, Rui Zhang, Wenchao Wu, Jiyu Luo, Haoran Geng, Xin Yang, Chen Cao, Yuemin Wu, Cheng Huang, Guodong Yang, Liping Zhang

Abstract: …Herschel reconstructs operator executions and cross-process dependencies to identify inefficiency mechanisms and suggest solutions using applicable reference fixes. AI agents implement and test engine and kernel changes under controlled conditions that preserve the triggering workload and dependencies, with expert review before deployment. Controlled tests… ▽ More Model-as-a-service platforms call for continuous optimization as complex serving conditions expose inefficiencies missed before deployment. Detailed always-on profiling can incur substantial overhead, while lightweight collection omits information needed for diagnosis. We present Herschel, a continuous optimization system for production large language model (LLM) inference. Our key insight is that adaptive, on-demand profiling can provide rich full-stack evidence without continuous collection. Herschel safely attaches to and detaches from selected running processes without engine changes or restarts, and adapts coverage as investigations reveal missing evidence. Herschel reconstructs operator executions and cross-process dependencies to identify inefficiency mechanisms and suggest solutions using applicable reference fixes. AI agents implement and test engine and kernel changes under controlled conditions that preserve the triggering workload and dependencies, with expert review before deployment. Controlled tests show active-collection overhead below 0.5% for time to first token and 7% for time per output token. Bounded windows, typically 30 s, avoid the continuous cost of always-on tracing. Over six months, Herschel collected approximately 17,000 traces across over 120 model variants and more than 10 accelerator types, identifying inefficiency patterns in 23% of the traces. Representative findings guide widely deployed optimizations, including restructured synchronization, removal of unused computation, and improved operator implementations. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: 17 pages

STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction

Authors: Nathan Tsoi, Michael J. Munje, Tejas Oberoi, Rishab Maheshwari, Pengen Zheng, Tanush Chauhan, Peter Stone, Joydeep Biswas

Abstract: …robot navigation. However, it remains unclear whether VLMs can accurately understand complex social navigation scenes (e.g., inferring the spatial-temporal relations among agents and human intentions), which is essential for safe and socially compliant robot navigation. While some recent works have explored the use of VLMs in social robot navigation, no exis… ▽ More Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition, common-sense reasoning, and contextual understanding, capabilities that align with the nuanced requirements of social robot navigation. However, it remains unclear whether VLMs can accurately understand complex social navigation scenes (e.g., inferring the spatial-temporal relations among agents and human intentions), which is essential for safe and socially compliant robot navigation. While some recent works have explored the use of VLMs in social robot navigation, no existing work systematically evaluates their ability to meet these necessary conditions. In this paper, we introduce the Social Navigation Scene Understanding Benchmark (SocialNav-SUB), a Visual Question Answering (VQA) dataset and benchmark designed to evaluate VLMs for scene understanding in real-world social robot navigation scenarios. SocialNav-SUB provides a unified framework for evaluating VLMs against human and rule-based baselines across VQA tasks requiring spatial, spatiotemporal, and social reasoning in social robot navigation. Through experiments with state-of-the-art VLMs, we find that while the best-performing VLM achieves an encouraging probability of agreeing with human answers, it still underperforms simpler rule-based approach and human consensus baselines, indicating critical gaps in social scene understanding of current VLMs. Our benchmark sets the stage for further research on foundation models for social robot navigation, offering a framework to explore how VLMs can be tailored to meet real-world social robot navigation needs. An overview of this paper along with the code and data can be found at https://larg.github.io/socialnav-sub. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: Conference on Robot Learning (CoRL) 2026. First two authors contributed equally. Project site: https://larg.github.io/stars/

EviRover: Reinforcing Agentic Perception Beyond a Glance

Authors: Kaixuan Fan, Kaituo Feng, Tianshuo Peng, Yilei Jiang, Manyuan Zhang, Junke Wang, Xiangyu Yue

Abstract: …visual details or require knowledge-intensive and up-to-date information. We term such cases \textit{perception under insufficient evidence} and formulate perception as an agentic process that can obtain information beyond a single glance. To address the absence of data for this setting, we design two dedicated data generation pipelines, yielding EviRover-SF… ▽ More Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's parametric knowledge suffice to resolve the query. This assumption often fails in real-world scenarios that hinge on fine-grained visual details or require knowledge-intensive and up-to-date information. We term such cases \textit{perception under insufficient evidence} and formulate perception as an agentic process that can obtain information beyond a single glance. To address the absence of data for this setting, we design two dedicated data generation pipelines, yielding EviRover-SFT-5K and EviRover-RL-12K for training. We further construct EviLens, a human-verified benchmark comprising 688 instances across five perception categories. Building on these data, we present EviRover, to our knowledge the first perception agent explicitly trained to resolve perceptual queries through interaction, using supervised fine-tuning followed by agentic reinforcement learning. Experiments show that the 4B EviRover outperforms its backbone by 30 points on average on EviLens, reaching performance comparable to advanced proprietary models. The gains transfer beyond EviLens to WebEyes, conventional perception benchmarks, and general multimodal benchmarks, including a 15-point improvement on BrowseComp-VL. All code, models, and data are released. △ Less

Submitted 30 September, 2026; originally announced September 2026.

PhantomEnvironments: Training LLM Agents in Fictional Worlds

Authors: Anmol Kabra, Swathi Saravana Selvam, Albert Gong, Chao Wan, Christian Belardi, Dongyoung Go, Katie Z. Luo, Kilian Q. Weinberger

Abstract: Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained… ▽ More Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments generated entirely by rules, whose generation requires no LLM and has zero marginal cost. We build PhantomEnvironments, multi-turn RL environments from fictional worlds, where agents must search a corpus of templated articles to answer multi-hop questions. Despite sharing no facts with the real world, these strikingly simple environments yield agents that transfer to real-world multi-hop search benchmarks, often outperforming real-world training data on newer benchmarks. Trained agents generalize to unseen fictional universes, and Qwen models learn to scale their search budget roughly linearly with question difficulty, suggesting emergent search scaling from environment interaction alone. Ablating environment complexity reveals that hop count drives transfer more than constraints or comparisons: even the simplest rule-generated environments are a surprisingly effective, free resource for training generalizable LLM agents. △ Less

Submitted 30 September, 2026; originally announced September 2026.

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

Authors: Guangzhi Xiong, Xinyuan Zhang, Xiao Yang, Hyokun Yun, Kai Zhang, Shiun-Zu Kuo, Hyeonjeong Ha, Xilun Chen, Kai Sun, Lucas Liang, Guangqiang Dong, Ejaz Ahmed, Ahmed A Aly, Anuj Kumar, Raffay Hamid, Aidong Zhang, Xin Luna Dong

Abstract: …To address these challenges, we introduce MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader. Without training or query-time video access, MemLife improves over the strongest training-free baseline by 4.6--12.0% across four long-horizon benchmarks. To further im… ▽ More Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessing raw clips for every query becomes computationally prohibitive. Memory systems offer a scalable alternative by compacting videos into text representations, but often fail on practical benchmarks: either the memory does not preserve key evidence, or the retriever fails to locate relevant entries due to retrieval competition in growing search spaces. To address these challenges, we introduce MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader. Without training or query-time video access, MemLife improves over the strongest training-free baseline by 4.6--12.0% across four long-horizon benchmarks. To further improve memory quality, we propose MemOpt, a reinforcement learning framework that optimizes the memory writer to produce faithful, informative, and retrievable memories. MemOpt consistently improves MemLife by 2.7--5.0% across different video and question distributions, with gains that generalize across writer and reader backbones and memory systems. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Learning from Research: Toward Lifelong Agent Harness Evolution

Authors: Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Yaar Harari, Evgeniy Gabrilovich, Shiyu Chang

Abstract: Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the… ▽ More Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness, the software that governs tool use, memory management, and task execution, while keeping the underlying language model fixed. Recent methods automate this process by using a meta coding agent to modify the harness based on execution feedback. However, relying on that agent's existing knowledge and observed failures can restrict exploration and make adaptation reactive. Inspired by how human experts learn from the research literature for new solutions, we introduce ScholarEvolve, a framework that automatically draws on state-of-the-art research to guide harness evolution. ScholarEvolve organizes the harness evolution directions into functional modules and uses topic modeling to identify distinct improvement strategies for each module. It implements these strategies and evaluates their combinations to improve task performance. Moreover, the framework is designed to incorporate new publications over time, allowing research advances to drive proactive lifelong evolution. Experiments demonstrate improvements on AppWorld and Tau2-Bench. ScholarEvolve raises Qwen3.5-27B task goal completion from 49.6% to 63.6% on AppWorld Challenge, and raises GPT-5.4-mini pass@1 from 72.7% to 81.9% on Tau2-Bench Telecom. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Reinforcement Learning-Guided Graph Transformations for SpTRSV Optimization

Authors: Buse Yılmaz

Abstract: …proposes a reinforcement learning-guided graph transformation framework for SpTRSV, in which graph transformation is formulated as a sequential decision-making problem and an RL agent learns matrix-dependent transformation policies. Experimental results on real-world sparse matrices demonstrate level reductions of up to 94% and reductions of up to 80% in the… ▽ More Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering applications. However, the data dependencies inherent in sparse triangular matrices significantly limit the available parallelism and make efficient workload distribution challenging. Recent graph transformation techniques address these limitations by modifying the dependency graph of the input matrix to improve parallel execution. Existing graph transformation strategies, however, rely on manually designed heuristics, making their development and adaptation to different optimization objectives challenging. This work proposes a reinforcement learning-guided graph transformation framework for SpTRSV, in which graph transformation is formulated as a sequential decision-making problem and an RL agent learns matrix-dependent transformation policies. Experimental results on real-world sparse matrices demonstrate level reductions of up to 94% and reductions of up to 80% in the coefficient of variation of level costs, while modifying only 1.50% of the rows in the highest case. On average, the RL- guided graph transformation achieves a 23% reduction in the number of levels and a 29% reduction in the coefficient of variation of level costs while rewriting only 0.82% of the matrix rows. Although the heuristic strategies generally achieve more aggressive level reduction(between 31% and 46%), the RL-based approach achieves the largest average reduction in the coefficient of variation of level costs, demonstrating its ability to balance competing graph transformation objectives. The results further show that the learned policies can be transferred to previously unseen matrices through curriculum learning and fine-tuning, while zero-shot experiments provide insights into the limitations of generalizing graph transformation policies across different sparsity patterns. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: 33 pages, 3 figures, 7 tables. Submitted to The Journal of Supercomputing and currently under review

QuLoC: Photonic Quantum-Assisted Low-Rank LLM Compression

Authors: Xiao-Hui Ni, Yu-Han Yao, Yu-Ze Zhu, Hang Song, Xiang Zhao, Lin Yang, Xian-Min Jin

Abstract: …to simulation, suggesting robustness to hardware noise. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks. ▽ More As LLMs grow in size, compression becomes increasingly important for efficient deployment. SVD-based low-rank compression reduces parameter counts but can degrade downstream performance. To improve performance after compression, we introduce QuLoC, a photonic quantum-assisted LLM compression algorithm that uses quantum circuit outputs to gate the retained low-rank components during training. Model performance is recovered through local functional reconstruction followed by end-to-end knowledge distillation. After training, the gating coefficients are absorbed into the low-rank factors, allowing the compressed model to run on classical hardware without executing quantum circuits during inference. Experiments on Qwen3.5-4B show that QuLoC achieves a 9.73\% relative improvement in average accuracy over state-of-the-art baselines across multiple downstream tasks, demonstrating its effectiveness. We further evaluate QuLoC on LLaMA-7B at different parameter compression ratios. It consistently achieves higher average downstream accuracy than state-of-the-art baselines, supporting its applicability to a larger model across different compression settings. Notably, experiments using the photonic quantum hardware retain these benefits with a small accuracy loss relative to simulation, suggesting robustness to hardware noise. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks. △ Less

Submitted 30 September, 2026; originally announced September 2026.

From DNA Design to DNA Slimming: Auditable Agentic Discovery of a Deletion-Only Designer

Authors: Joel Shor

Abstract: …indices, which can be used to verify that the slimmer obeyed task requirements. To our knowledge, this is the first dedicated benchmark of this deletion-only problem. The coding agent Empirical Research Assistant (ERA) then searched over executable designer programs. ERA received the task prompt and a successful substitution-only designer GrAdaBeam as a star… ▽ More Compact regulatory DNA can free up space in vector payloads, reduce synthesis and assay burden, and expose which sequence features drive predicted activity. Yet most model-based nucleic-acid designers optimize fixed-length sequences through substitutions; they do not ask which bases of an existing functional element can be removed while retaining predicted activity. We define the task of sequence slimming as selecting an exact-length, order-preserving subsequence while retaining activity. Modeled on the design benchmark NucleoBench, we propose a quantitative evaluation for slimming that balances sequence reduction with maintaining function. Each slimmer must return both the subsequence and its source indices, which can be used to verify that the slimmer obeyed task requirements. To our knowledge, this is the first dedicated benchmark of this deletion-only problem. The coding agent Empirical Research Assistant (ERA) then searched over executable designer programs. ERA received the task prompt and a successful substitution-only designer GrAdaBeam as a starting program, and it modified the designer to produce GRADASLIM. We report held-out evaluations for five transcription-factor binding targets, comparing random, greedy, and ERA-guided slimming at 400 and 100 bp. ERA has the highest mean in 9/10 settings. Paired bootstrap intervals for ERA minus greedy are above zero in all five 400-bp settings, below zero in one 100-bp setting, and overlap zero in the remaining four. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: Agentic AI for Biological Discovery

Game-Guided Skill Discovery through Self-Play for Playable Agent Control

Authors: Seungeun Rho, Jeonghwan Kim, Xue Bin Peng, Sehoon Ha

Abstract: …a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a compact abstraction for controlling embodied agents through a small set of learned behaviors rather than low-level actions. To be effective, these skills should be semantically distinct, interpretable, and expressive; properties… ▽ More We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a compact abstraction for controlling embodied agents through a small set of learned behaviors rather than low-level actions. To be effective, these skills should be semantically distinct, interpretable, and expressive; properties that existing unsupervised skill-discovery methods often fail to achieve simultaneously. GGSD achieves these desiderata by grounding skill discovery in competitive gameplay. A hierarchical agent competes against its past selves, with a high-level policy selecting from a small discrete skill set and a skill-conditioned low-level policy learning the corresponding behaviors. After training, a human can replace the high-level policy and directly control the agent through the same discrete skills. Despite the small number of high-level actions, skill transitions give rise to emergent combo behaviors, expanding expressivity beyond individual primitives. Across Ant, Franka-arm, and Unitree G1 environments, we show that GGSD produces human-playable skills that humans can compose to solve unseen tasks, such as Maze and CubePush, without additional training. An interactive demo is available at https://ggsd-demo.github.io. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Tactile Curiosity Drives Robot Interaction

Authors: Klemens Iten, Alexander Proshkin, Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza

Abstract: …skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge. Existing intrinsic motivation methods based… ▽ More Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge. Existing intrinsic motivation methods based on model disagreement or epistemic uncertainty improve on isotropic noise, but they can also reward uncertainty in functionally irrelevant transitions, such as erratic motions in free space. In this work, we argue that tactile feedback provides a natural signal for exploration, and introduce TacEx, a framework that incorporates touch into epistemic uncertainty-driven exploration by decomposing model uncertainty across sensory modalities and directing curiosity toward the tactile channel. By anchoring curiosity to the sense of touch, TacEx drives the robot to discover complex contact dynamics, learning to manipulate and grasp objects without task rewards or expert demonstrations during exploration. The interaction-dense dataset collected through this tactile-driven curiosity supports offline learning of downstream pick-and-place policies without additional environment interaction. We further use tactile-driven exploration to post-train vision-language-action (VLA) models. Although the VLAs are initially pre-trained without tactile feedback, post-training with TacEx substantially improves downstream performance while remaining highly sample-efficient. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Comments: 16 pages, 6 figures, 1 table. Preprint, under review

Who Asked for This? Inline Annotations as Authoring Transactions for Provenance in Agentic Authoring

Authors: Chang Xiao

Abstract: Writing with AI agents turns a paragraph into the outcome of many requests, yet the finished document rarely explains which request produced which change. We introduce Reactant, an interaction paradigm in which authors place typed inline annotations in their original documents. A verified transaction protocol records each request, skill identity, and the cor… ▽ More Writing with AI agents turns a paragraph into the outcome of many requests, yet the finished document rarely explains which request produced which change. We introduce Reactant, an interaction paradigm in which authors place typed inline annotations in their original documents. A verified transaction protocol records each request, skill identity, and the correspondences that identify additions, deletions, and transformations. The kernel validates the witness against the recorded states to establish word-level longitudinal lineage. We demonstrate Reactant through this paper's revision history, and report four months of three colleagues' self-directed use. Their uses include conversational inquiry into history and deriving reusable skills from recurring requests, illustrating how the transaction record serves as an extensible substrate for agentic authoring. △ Less

Submitted 30 September, 2026; originally announced September 2026.

Persistent Context Graphs for Efficient Memory Compaction in LLM Agents

Authors: Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Zhaoxuan Tan, Pei Zhou, Mengting Wan, Yaar Harari, Evgeniy Gabrilovich, Shiyu Chang

Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compaction essential for staying within context windows and reducing prefill cost. Existing methods summarize the history or compress its KV cache, often adding model computation to preserve information for future… ▽ More As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compaction essential for staying within context windows and reducing prefill cost. Existing methods summarize the history or compress its KV cache, often adding model computation to preserve information for future requests. A new user request can change which history matters, but reassessing that history with the model requires re-encoding it if the KV cache has expired. Past attention provides signals of historical importance and dependencies between messages, while relevance to the current task must be assessed using the new user request. We introduce ReCAP, a memory compaction method that stores attention-derived importance scores and dependency links in a lightweight, persistent context graph. For each new request, ReCAP combines stored importance with relevance cues from the request and follows dependency links to select messages and their supporting context, without additional model calls for selection. Compared with Codex's default summarization-based compaction, ReCAP reduces estimated latency for compaction and cold restoration by approximately 95% on both Qwen3-Coder and gpt-oss. It also roughly halves the historical context per call on SWE-Together at comparable task quality and improves accuracy on the code tasks of Lost-in-Conversation over full history by 19.8 and 41.2 points. △ Less

Submitted 30 September, 2026; originally announced September 2026.