arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

2025-11-13 至 2025-11-13 共收录 10 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. Agent评测 10 篇

2511.09030 2025-11-13 cs.AI cs.CL cs.MA 82%

Solving a Million-Step LLM Task with Zero Errors

Elliot Meyerson, Giuseppe Paolo, Roberto Dailey, Hormoz Shahrzad, Olivier Francon, Conor F. Hayes, Xin Qiu, Babak Hodjat, Risto Miikkulainen

机构 * Cognizant AI Lab(Cognizant AI实验室) UT Austin(得克萨斯大学奥斯汀分校)

专题命中 Agent评测 :agent(abstract);tool use(abstract);agentic(abstract);multi-agent(abstract)

Comments Main paper: 14 pages, 29 pages with references and appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.09074 2025-11-13 cs.RO 67%

Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives

Letian Wang, Marc-Antoine Lavoie, Sandro Papais, Barza Nisar, Yuxiao Chen, Wenhao Ding, Boris Ivanovic, Hao Shao, Abulikemu Abuduweili, Evan Cook, Yang Zhou, Peter Karkus, Jiachen Li, Changliu Liu, Marco Pavone, Steven Waslander

专题命中 Agent评测 :agent(abstract);planning(abstract)

Comments (Book) To Appear in Foundation and Trends in Robotics. 163 pages, 40 figures, 13 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08835 2025-11-13 cs.CL cs.AI 62%

Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents

Yejin Yoon, Yuri Son, Namyoung So, Minseo Kim, Minsoo Cho, Chanhee Park, Seungshin Lee, Taeuk Kim

专题命中 Agent评测 :agent(abstract);分类 cs.AI、cs.CL

Comments accepted to EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08598 2025-11-13 cs.CL cs.AI 62%

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking

Yanhong Li, Tianyang Xu, Kenan Tang, Karen Livescu, David McAllester, Jiawei Zhou

机构 * University of Chicago(芝加哥大学) TTI-Chicago(芝加哥技术研究所) UC Santa Barbara(圣巴巴拉大学) Stony Brook University(石溪大学)

专题命中 Agent评测 :agentic(abstract);分类 cs.AI、cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08587 2025-11-13 cs.CY cs.AI cs.CL 62%

Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy Consumption

Shadaab Ghani, Anne Håkansson, Oleksii Pasichnyi, Hossein Shahrokni

机构 * KTH Royal Institute of Technology(皇家理工学院)

专题命中 Agent评测 :agent(abstract);分类 cs.AI、cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08866 2025-11-13 cs.CL 57%

BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generation

Fuyi Yang, Chenchen Ye, Mingyu Derek Ma, Yijia Xiao, Matthew Yang, Wei Wang

机构 * University of California, Los Angeles(加州大学洛杉矶分校)

专题命中 Agent评测 :agent(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15201 2025-11-13 cs.RO cs.AI 57%

Survey of Vision-Language-Action Models for Embodied Manipulation

Haoran Li, Yuhui Chen, Wenbo Cui, Weiheng Liu, Kai Liu, Mingcai Zhou, Zhengtao Zhang, Dongbin Zhao

专题命中 Agent评测 :agent(abstract);分类 cs.AI

Comments in Chinese language

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.08130 2025-11-13 q-bio.PE physics.bio-ph 50%

An Elementary Microscopic Model of Sympatric Speciation

Franco Bagnoli, Tommaso Matteuzzi

专题命中 Agent评测 :agent(abstract)

Comments 11 pages, 5 figures

Journal ref Theor. Biol. Forum: 117, 85-110 (2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08742 2025-11-13 physics.soc-ph cond-mat.stat-mech 50%

The Emergence of Socio-Economic Structure: A First-Principles Kinetic Theory

Miguel A. Durán-Olivencia

专题命中 Agent评测 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08707 2025-11-13 eess.IV cs.IT math.IT 50%

Compositional Distributed Learning for Multi-View Perception: A Maximal Coding Rate Reduction Perspective

Zhuojun Tian, Mehdi Bennis

专题命中 Agent评测 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏