Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site vi do unit it site zenodo org site:arxiv.org” of 46 matched · 776 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below
https://arxiv.org/html/2608.02613v1
Instead, it falls on local, personal agents to effectively and safely maintain/utilize such dense person-person (PP) and person-agent (PA) interaction histories
https://arxiv.org/html/2608.02918v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/list/cs.AI/new
Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state
https://arxiv.org/html/2608.03048v1
6 million tokens and find that it outperforms the recurrent-memory baseline by +6
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2608.00028v1
Using a controlled disturbance-rejection testbed with an exactly computable optimum, we show this conclusion is too strong and replace it with a quantitative resource model built on three resources: population width NN, per-agent internal-model memory dd, and prediction across the observation delay τ\tau
https://arxiv.org/html/2607.27188v1
org perpetual non-exclusive license
arXiv:2607
https://arxiv.org/html/2608.03095v1
We release codes and datasets at https://github
https://arxiv.org/list/cs.CL/new
With the interaction history, it co-generates ground truth over six recall, reasoning, and trustworthiness evaluation dimensions
https://arxiv.org/html/2407.16741v3
edu
Abstract
Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways
https://arxiv.org/html/2608.00328v2
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2607.26245v1
We do not claim trading profitability—the central empirical finding is the opposite, and that negative result is published with the data that produced it
https://arxiv.org/html/2608.02668v1
com/hazdzz/deep_connection \ncudata[Correspondence]Jie Zhang (),
Correspondence: Cheng-Fang Su ()
“Geometry is not true, it is advantageous
https://arxiv.org/html/2407.04503v4
2 To what extent do multi-turn transmissions affect the evolution of properties
https://arxiv.org/html/2608.03063v1
Compared with the production DeepSeek-based LLM baseline, it improves screening precision from 92
https://arxiv.org/list/math/new
It is natural to expect that if many pairs $(x_i,x_j)$ lie at distance close to $1$ from each other, then some clustering phenomenon must occur, implying that a significant number of these pairs are also very close to each other
https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking
https://arxiv.org/list/cs.SE/current
Skip to main content Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Software Engineering
Authors and titles for August 2026
Total of 314 entries : 1-50 51-100 101-150 151-200 ... 301-314
Showing up to
https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation
https://arxiv.org/list/eess/current
Barrios-Muñoz, Azim Akhtarshenas
Comments: The dataset for this manuscript and also prepared code will be uploaded to Zenodo and GitHub and will be updated here with new versions
Subjects: Signal Processing (eess
https://arxiv.org/list/cs.IR/recent
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
Authors and titles for recent submissions
Wed, 5 Aug 2026
https://arxiv.org/list/cs.CY/current
Also archived at Zenodo: this https URL
Subjects: Computers and Society (cs
https://arxiv.org/list/cs.PF/current
Skip to main content Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Performance
Authors and titles for August 2026
Total of 47 entries
Showing up to 50 entries per page: fewer | more | all
[1] arXiv:
https://arxiv.org/list/q-fin.TR/new
Companion dataset: Zenodo concept DOI https://doi
https://arxiv.org/html/2608.02620v1
This fragmentation makes it difficult to study how design choices—the benchmark, the judge model, the prompt, the inference backend—affect the conclusions we draw about model quality
https://arxiv.org/list/cs.IR/new
To handle it, KGD assigns them to separate parameter sets: a refreshable encoder owns behavioral knowledge, while a task learner reads contextualized encoder states through read-only cross-attention and writes task-specific geometry through Anchored Calibration Residual (ACR) orthogonal to the pretrained embedding
https://arxiv.org/abs/2603.24755
Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it impossible to faithfully measure how their decisions shape future extensions
https://arxiv.org/html/2608.02999v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/abs/2608.12700
Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept it if the output is close to a reference