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。

2025-10-09 至 2025-10-09 共收录 8 篇信号源：cs.AI, cs.CL, cs.LG, cs.SE

1. 记忆与上下文管理 8 篇

2510.06727 2025-10-09 cs.CL cs.AI cs.LG 83%

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management

Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen

机构 * Stanford University（斯坦福大学）； Carnegie Mellon University（卡内基梅隆大学）

专题命中记忆与上下文管理：agent(abstract)；tool use(abstract)；tool-use(abstract)；function calling(abstract)

2502.12110 2025-10-09 cs.CL cs.HC 83%

A-MEM: Agentic Memory for LLM Agents

Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang

机构 * Rutgers University（罗杰斯大学）

专题命中记忆与上下文管理：agentic(title,abstract)；agent(abstract)；分类 cs.CL

Comments Advances in Neural Information Processing Systems (NeurIPS 2025)

2510.07266 2025-10-09 cs.LG cs.GT 57%

Dynamic Regret Bounds for Online Omniprediction with Long Term Constraints

Yahav Bechavod, Jiuyao Lu, Aaron Roth

机构 * Department of Computer and Information Sciences, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学）； Department of Statistics and Data Science, University of Pennsylvania（统计与数据科学系，宾夕法尼亚大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2510.06664 2025-10-09 cs.CL 57%

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory

Yunzhong Xiao, Yangmin Li, Hewei Wang, Yunlong Tang, Zora Zhiruo Wang

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Rochester（罗切斯特大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

2410.15492 2025-10-09 cs.LG cs.OS 57%

Reinforcement Learning for Dynamic Memory Allocation

Arisrei Lim, Abhiram Maddukuri

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2408.01753 2025-10-09 cs.MA cs.SY eess.SY math.DS math.OC nlin.AO 50%

Opinion Dynamics with Set-Based Confidence: Convergence Criteria and Periodic Solutions

Iryna Zabarianska, Anton V. Proskurnikov

专题命中记忆与上下文管理：agent(abstract)

2306.04331 2025-10-09 physics.bio-ph cond-mat.soft q-bio.BM 50%

Towards a Benchmark for Markov State Models: The Folding of HP35

Daniel Nagel, Sofia Sartore, Gerhard Stock

专题命中记忆与上下文管理：workflow(abstract)

Comments arXiv admin note: text overlap with arXiv:2303.03814

2510.06222 2025-10-09 cs.HC econ.GN q-fin.EC 50%

Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making

Ziv Ben-Zion, Zohar Elyoseph, Tobias Spiller, Teddy Lazebnik

专题命中记忆与上下文管理：autonomous agent(abstract)

Comments Manuscript Main Text - 20 pages, including 3 Figures and 1 Table. Supplementary Materials - 10 pages, including 4 Supplemental Tables