LatentSift is a token‑free, execution‑free filtering method for software engineering agents that replaces the initial LLM‑based verifier. It represents each candidate trajectory using the policy’s hidden states—reasoning, observation, and function‑call states—and compares them against banks of successful and unsuccessful states collected during training. By fusing distance scores with a learned linear score, LatentSift retains promising candidates, reducing EF‑verifier tokens by 66.6–81.0% and total verification tokens by 49.1–62.1% while maintaining or improving performance on DeepSWE‑Preview.
By Yuning Han, Yangchenchen Jin, Tyler Jandreau, Jingwei Sun
The study audits the cultural values expressed by the decision‑only language model JEV using the 2013 Values Survey Module. By presenting 24 items to JEV under 12 matched Saudi and 12 matched American personas, in both English and Arabic, and across eight request formulations, the researchers found that JEV’s responses were highly repeatable (ICC 0.997) and that persona and language significantly influenced the model’s value profiles. Saudi personas shifted JEV’s answers toward the human Saudi‑US difference—capturing 87 % of the effect in English and 62 % in Arabic—while language, age, and gender also modulated the outcomes.
By Bushra Asseri, Abdulaziz Asseri
arXiv:2609.37056v1 Announce Type: cross
Abstract: Evolutionary program search driven by large language models (LLMs) has produced record-breaking constructions for open problems in combinatorics and...
By Amal Seddas, Vladyslav Shashkov, Maryna Viazovska, Emmanuel Abbe
The paper investigates patch‑wise supervision for detecting AI‑generated images, proposing a shared backbone that classifies explicit crops with individual losses and averages patch probabilities only during inference. This approach eliminates the need for handcrafted residual filtering or learned image‑level fusion modules. Experiments across single‑patch selection, multiple generator collections, and four CNN and Transformer backbones show that patch‑wise variants outperform whole‑image counterparts on the GenImage dataset, while also exploring factors such as supervision granularity, source resolution, crop size, and inference coverage.
By Zhida Zhang, Tao Wu, Siyu Liu, Jie Cao
arXiv:2605.24539v2 Announce Type: replace
Abstract: Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior....
By Lirong Che, Yuzhe yang, Peiwen lin, Xu Cao, Chuang wang, Xueqian wang, Jian su
arXiv:2602.13540v2 Announce Type: replace-cross
Abstract: Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on...
By Sin-Han Yang, Cheng-Kuang Wu, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee, Shao-Hua Sun
Block Sparse Flash Attention (BSFA) is a drop‑in replacement for FlashAttention that speeds up long‑context inference by pruning about 50% of computation and memory transfers. It selects the top‑k most important value blocks for each query using exact query‑key similarities and calibrated per‑layer, per‑head thresholds, requiring only a one‑time training‑free calibration. On Llama‑3.1‑8B, BSFA delivers up to 1.13× speedup on LongBench with a 1.1% accuracy drop and up to 1.24× on Needle‑in‑a‑Haystack retrieval with a 1% drop, while the attention kernel itself accelerates by up to 1.38×.
By Daniel Ohayon, Itay Lamprecht, Itay Hubara, Israel Cohen, Daniel Soudry, Noam Elata
OMP-MoE is a training‑free compression framework that prunes redundant experts in Mixture‑of‑Experts large language models by framing the problem as sparse signal reconstruction solved with Orthogonal Matching Pursuit. The method greedily selects expert contributions as dictionary atoms to minimize reconstruction error, then optimizes cross‑layer expert allocation via a water‑filling strategy, and finally introduces an adaptive inference mechanism (OMP‑MoE†) that dynamically adjusts expert activation based on energy prediction. Experiments on Qwen, DeepSeek‑V2, GPT‑OSS, and Mixtral MoE show consistent performance gains at 25‑50% pruning ratios, with Qwen3‑30B‑A3B retaining 93.3% of original performance at 50% compression while achieving significant speedups.
By Dezhi Li, Lujun Li, Qiyuan Zhu, Hao Gu, Bei Liu, Sirui Han, Yike Guo
The paper introduces Knowledge-Aware Semantic Bridging (KASB), a framework designed to improve Retrieval-Augmented Generation (RAG) by aligning the semantic spaces of queries and retrieved contexts. KASB achieves this through intelligent fusion of generative and retrieval-based knowledge in a multistage process, aiming to enhance passage selection quality, relevance, and accuracy. The authors evaluate the method on three popular open-domain Question Answering datasets, demonstrating its effectiveness.
By Xinkai Du, Chao Lv, Yalin Sun, Quanjie Han, Lei Yao, Maosong Sun
Large Language Model judges are commonly used to rank texts via pairwise comparison, with reliability traditionally measured by position bias, transitivity, and pairwise agreement. This paper argues that these proxies are misleading because they are dominated by close‑rank‑gap pairs, which contribute little to the overall ranking, while far‑gap pairs carry the true ranking signal. Experiments on simulations and human‑rated corpora show weak correlation between the proxies and actual ranking accuracy, suggesting judges should be evaluated using rank‑gap‑conditional metrics against human rankings.
By Bruno Brocai, Maria Becker
The paper introduces SCSP, a training‑free framework that improves long‑context embeddings by selectively pooling informative tokens. SCSP partitions documents into sentence‑aware chunks, adds a semantic compression prompt to each chunk, and uses prompt‑isolated attention masks to estimate token importance. The selected tokens’ intermediate‑layer representations are aggregated to form the final embedding, yielding consistent performance gains across zero‑shot and fine‑tuned models on long‑context benchmarks.
By Zifeng Cheng, Jie Zheng, Zhiwei Jiang, Shuwen Wang, Fei Shen, Shiping Ge, Qing Gu
The paper introduces LongHarness Bench, a new benchmark designed to evaluate both the effectiveness and efficiency of language model harnesses for long-context reasoning. It features tasks that require diverse retrieval strategies—such as lexical search and semantic matching—and strategic, adaptive reasoning over global and local context, with only a small subset of the context being useful at each step. Evaluations across multiple state‑of‑the‑art models and harnesses show that even strong combinations achieve only 68% macro‑average accuracy, and that the same model can vary markedly in efficiency depending on the harness used.
By Quang Hieu Pham, Thuy Duong Nguyen, Jocelyn Qiaochu Chen, Xi Ye
TTMark introduces a pairwise watermarking framework that extends distortion‑free watermarking from single tokens to adjacent token pairs, enlarging the watermarking alphabet from V to V². By watermarking the joint distribution of consecutive tokens, the detector can exploit both token entropy and conditional entropy while maintaining distortion‑freeness. Experiments on multiple language models and datasets show that TTMARK improves detectability, robustness to edits, and localized watermark detection without degrading generation quality.
By Ruibo Chen, Zhengmian Hu, Donghang Lu, Xuehao Cui, Georgios Milis, Yihan Wu, Jian Du, Heng Huang
arXiv:2608.25466v2 Announce Type: replace-cross
Abstract: The functional annotation of genes in non-model organisms remains a significant challenge in computational biology, with 20-70% of sequenced...
By Azrin Sultana
arXiv:2609.32352v2 Announce Type: replace-cross
Abstract: Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging r...
By Gujie Shao, Zixun Xie, Xuechun Xing, Ruixiang Wang, Ziyun Lan, Yanlin Qi, Gangyi Zhang, Yuxin Yang, Dawei Li, Haiming Tang
arXiv:2502.04492v3 Announce Type: replace
Abstract: The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive framew...
By Selim Furkan Tekin, Gaowen Liu, Ramana Rao Kompella, Ling Liu
arXiv:2601.03418v3 Announce Type: replace
Abstract: Trustworthy clinical summarization requires every claim to be traceable to its evidence, yet existing attribution often resolves only to the senten...
By Bohao Chu, Hendrik Damm, Tabea M. G. Pakull, Sameh Frihat, Georg Lodde, Elisabeth Livingstone, Christoph M. Friedrich, Norbert Fuhr
arXiv:2604.15490v2 Announce Type: replace
Abstract: Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical...
By Eleanor M. Lin, David Jurgens
arXiv:2609.36957v1 Announce Type: new
Abstract: Direct visual readability and task-information recoverability are different quantities. Failure to decode a target from a fixed observation need not el...
By Yiwei Liu
The paper introduces Learner2Skill, a method that transforms historical learner interactions into a reusable Simulation Skill. This Skill encapsulates a learner’s current state and recurring response patterns, allowing it to evolve with new interactions and be adapted to different LLMs without reconstructing the learner from scratch. Experiments demonstrate that Learner2Skill more accurately reproduces fine‑grained learner behavior while reducing token costs and enabling cross‑LLM reuse.
By Zijian Chen, Zheng Zhang, Miao Jia, Xingchen Hu, Weibo Gao, Linan Yue