TSFLab is a self‑improving, agent‑agnostic workbench designed to streamline time‑series forecasting research. It equips coding agents with shared resources and tools, enabling low‑cost experimentation, reproducibility, and continuous maintenance of research artifacts. Experiments show that TSFLab boosts task completion rates by 20‑163% and reduces token usage and development time significantly compared to baseline approaches.
By ChengAo Shen, Yanjun Zhao, Haoxin Liu, Bonnie Chen, Miles Ma, Dongjin Song, Hanghang Tong, Qingsong Wen, Jingrui He, Jingchao Ni
arXiv:2610.40753v1 Announce Type: cross
Abstract: Coding agents increasingly rely on automated approvers to decide whether a proposed shell command may run. Existing approvers, from rule-based checke...
By Weiheng Wu, Junkai Chen, Zhensu Sun, Jieke Shi, Yunbo Lyu, David Lo
arXiv:2610.41124v1 Announce Type: new
Abstract: Agentic LLM assistants must repeatedly decide whether to answer from memory or to call a tool such as web search. Unnecessary searches cost latency and...
By Nipun D. Pathirage, Kwan Srijomkwan
arXiv:2610.41112v1 Announce Type: new
Abstract: Quantization of Large Language Models (LLMs) has be- coming increasingly important for reducing the computa- tional costs and resource requirements for...
By Jing Huang, Yu Cheng, Ziwei Yu, Lan Zhao, Sitan Li, Guangxiu Yao, Xin Wang, Yuanyong Luo, Hengyi Liang, Ting Li, Bo Liu, Hu Liu, Michael Bi Mi, Heng Liao
arXiv:2610.40735v1 Announce Type: cross
Abstract: Evaluating approaches that improve the security of LLM code generation requires datasets that jointly assess security and functionality and remain ad...
By Zacharie Chenail-Larcher, Daniele Lunghi, Melissa Tessa, Quentin Sti\'evenart, Jacques Klein, Tegawend\'e F. Bissyand\'e, Florent Avellaneda, Naouel Moha
arXiv:2610.40758v1 Announce Type: new
Abstract: Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them. An agen...
By Chenjie Qiu, Boyan Xu, Shaobin Shi, Bingfeng Chen, Ruichu Cai, Dongsheng Luo
arXiv:2610.40798v1 Announce Type: new
Abstract: Web world models increasingly predict the consequences of candidate actions before agents act, yet a plausible predicted future does not necessarily su...
By Zhifei Hu, Alexandra I. Cristea, Adel Bibi, Jialin Yu
arXiv:2610.41129v1 Announce Type: new
Abstract: AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks inf...
By Hanzhao Wang, Shengjie Liu, Zhengchao Wang
arXiv:2610.42004v1 Announce Type: new
Abstract: Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing...
By Xiangyu Kong, Ruirui Yang, Xia Hou
arXiv:2610.42116v1 Announce Type: new
Abstract: In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model invocation toward heterogeneous deployments i...
By Yuzhe Liu, Haolin Tian, Tonghan Wang
arXiv:2610.41486v1 Announce Type: new
Abstract: While prior work has highlighted that systematic nation-level bias in large language models (LLMs) can pose operational risks for international relatio...
By Jonghyeon Choi, Yeonjun Choi, Beakcheol Jang
arXiv:2610.41368v1 Announce Type: new
Abstract: Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific...
By Russell Ro, Reza Abbasi-Asl
The paper introduces BILAL-BENCH, a 240-question benchmark designed to evaluate open-ended Islamic-source fabrication in Bengali. It assesses models on Qur'anic attribution, hadith, fiqh, contemporary issues, and adversarial prompts, using a rubric that separates source errors from assertiveness. Seven open-weight models were tested, revealing that most confidently fabricate on 79.3–95.3% of source-production questions, with hadith provenance being the weakest area and no clear improvement with larger model size.
By Sabah Nushra, Md Kishor Morol
P-ContextBench is a benchmark designed to evaluate how well large language models understand and safely use personal context. It creates realistic, life‑story‑grounded digital humans from U.S. demographic seeds, embedding traits, routines, goals, and constraints in fragmented, evolving synthetic mobile‑app records. The benchmark tests five capabilities—fact recovery, temporal tracking, pattern inference, and safe handling of conflicting requests—using a multi‑stage validation pipeline and 4,810 verified test cases.
By Grant Nasir Brown, Abdul Basir Bari, Anmol Tadikonda, Isabel Song
arXiv:2610.41025v1 Announce Type: new
Abstract: When a language-model agent fails a multi-step task, can another model find the decisive mistake and fix it with a single action? We introduce ReplayRC...
By Jeremy Canale, Fabien Soulis
arXiv:2610.41076v1 Announce Type: new
Abstract: An LLM agent that helps a patient get care must do two things. It must reach the correct outcome, and it must follow the necessary procedure. For examp...
By Shriram Vasudevan, Videet Mehta, Connor Sweeney
arXiv:2610.41710v1 Announce Type: new
Abstract: Clinical trial failures are a major barrier to efficient drug development, incurring substantial costs and delaying patient access to effective therapi...
By Burak Bakkar, Hana Moalla, Mohamed Salem Jedidi, Haifa Ben Messaoud, Nicolas Lopez Carranza
Learned sparse attention, used in production models such as DeepSeek-V4 and GLM-5, lets each query attend to only k keys chosen by a lightweight indexer, but the indexer still scores every key in the...
Cross-view object correspondence (CVOC) aims to establish associations of the same target between query and search videos captured from different viewpoints. Existing methods often rely on visual cues...
AI assistants store values that a language model derived from a person's records under the person's own definitions, such as their important contacts. Keeping such a value correct takes two steps: det...