AI Agent

Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics

Akshara Prabhakar, Roshan Ram, Zixiang Chen, Silvio Savarese, Frank Wang, Caiming Xiong, Huan Wang, Weiran Yao

机构 * Salesforce AI Research（Salesforce AI研究院） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)；planning(abstract)

Comments Technical report; 13 pages plus references and appendices

TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems

Ishan Kavathekar, Hemang Jain, Ameya Rathod, Ponnurangam Kumaraguru, Tanuja Ganu

机构 * International Institute of Information Technology, Hyderabad（国际信息科技研究所，海得拉巴） ； Microsoft Research, India（微软研究院，印度） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)；tool use(abstract)

Comments Accepted at ICML 2025 MAS Workshop. This version includes additional experiments and analysis

Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale

Bassel Al Omari, Michael Matthews, Alexander Rutherford, Jakob Nicolaus Foerster

机构 * University of Waterloo（滑铁卢大学） ； FLAIR, University of Oxford（牛津大学FLAIR研究所） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Data-Driven Mechanism Design using Multi-Agent Revealed Preferences

Luke Snow, Vikram Krishnamurthy

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)

ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations

Amr Gomaa, Ahmed Salem, Sahar Abdelnabi

机构 * German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI）） ； Microsoft（微软） ； ELLIS Institute Tübingen and MPI for Intelligent Systems（图宾根ELLIS研究所和智能系统研究所） ； Tübingen AI Center（图宾根人工智能中心） 纠错

专题命中 多智能体 ：agent(title,abstract)；autonomous agent(abstract)；tool use(abstract)；multi-agent(abstract)

A Composable Agentic System for Automated Visual Data Reporting

Péter Ferenc Gyarmati, Dominik Moritz, Torsten Möller, Laura Koesten

专题命中 多智能体 ：agentic(title)；agent(abstract)；AI agent(abstract)；multi-agent(abstract)

Communication-Constrained Private Decentralized Online Personalized Mean Estimation

Yauhen Yakimenka, Hsuan-Yin Lin, Eirik Rosnes, Jörg Kliewer

机构 * New Jersey Institute of Technology（新泽西理工学院） ； Newark, New Jersey 07102, USA（新泽西州纽克塞尔07102, 美国） 纠错

专题命中 多智能体 ：agent(abstract)；分类 cs.LG

Comments Paper accepted for presentation at the 2025 IEEE Information Theory Workshop (ITW 2025). Final conference version

Cooperation Under Network-Constrained Communication

Tommy Mordo, Omer Madmon, Moshe Tennenholtz

专题命中 多智能体 ：agent(abstract)

Distributed Stochastic Momentum Tracking with Local Updates: Achieving Optimal Communication and Iteration Complexities

Kun Huang, Shi Pu

专题命中 多智能体 ：agent(abstract)

Comments 29 pages, 8 figures