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。

2025-10-14 至 2025-10-14 共收录 7 篇信号源：cs.AI, cs.CL, cs.LG, cs.SE

1. 工具调用 7 篇

2508.08882 2025-10-14 cs.AI 90%

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li

机构 * Baidu Inc.（百度公司）； Peking University（北京大学）

专题命中工具调用：agent(title,abstract)；tool use(title,abstract)；tool-use(abstract)；multi-agent(abstract)

2508.16260 2025-10-14 cs.CL cs.AI 88%

MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use

Fei Lei, Yibo Yang, Wenxiu Sun, Dahua Lin

机构 * SenseTime Research（商汤科技研究院）

专题命中工具调用：tool use(title,abstract)；agentic(title,abstract)；分类 cs.AI、cs.CL

2406.14917 2025-10-14 cs.AI cs.CL cs.CV cs.LG cs.NE 82%

LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking

Melvin Wong, Jiao Liu, Thiago Rios, Stefan Menzel, Yew Soon Ong

机构 * 1 College of Computing \& Data Science (CCDS), Nanyang Technological University (NTU), Singapore 2 Honda Research Institute Europe (HRI-EU), Offenbach am Main, Germany 3 Centre for Frontier AI Research (CFAR), Agency for Science, Technology

专题命中工具调用：agentic(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments This work is accepted by IEEE CIM. IEEE copyrights applies

Journal ref IEEE Computational Intelligence Magazine (Volume: 20, Issue: 4, November 2025)

2509.00482 2025-10-14 cs.CL cs.AI cs.HC 73%

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting

Saksorn Ruangtanusak, Pittawat Taveekitworachai, Kunat Pipatanakul

机构 * SCBX R&D（SCBX研发部）； SCB 10X R&D（SCB 10X研发部）

专题命中工具调用：agent(abstract)；function calling(abstract)；分类 cs.AI、cs.CL

Comments EMNLP 2025 Wordplay Workshop (Spotlight)

2510.11536 2025-10-14 cs.SE cs.AI 62%

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

Manaal Basha, Aimeê M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodríguez-Pérez

机构 * University of British Columbia（不列颠哥伦比亚大学）； Federal University of Pará（帕拉联邦大学）

专题命中工具调用：workflow(abstract)；分类 cs.AI、cs.SE

Comments ICSME 2025 Tool Demonstration Track

2510.10009 2025-10-14 cs.CL cs.AI cs.IR 62%

Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning

Shu Zhao, Tan Yu, Anbang Xu

机构 * NVIDIA（英伟达）； Pennsylvania State University（宾夕法尼亚州立大学）

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

2510.10601 2025-10-14 math.DG math.AP 50%

Construction of harmonic coordinates for weak immersions

Dorian Martino, Tristan Rivière

专题命中工具调用：tool use(abstract)