AI Agent

LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead

Junda He, Christoph Treude, David Lo

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

Comments TOSEM 2030 Special Issue

Aime: Towards Fully-Autonomous Multi-Agent Framework

Yexuan Shi, Mingyu Wang, Yunxiang Cao, Hongjie Lai, Junjian Lan, Xin Han, Yu Wang, Jie Geng, Zhenan Li, Zihao Xia, Xiang Chen, Chen Li, Jian Xu, Wenbo Duan, Yuanshuo Zhu

机构 * ByteDance（字节跳动） 纠错

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

Comments 14 pages, 1 figures,

Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration

Xinyuan Song, Zeyu Wang, Siyi Wu, Tianyu Shi, Lynn Ai

机构 * Emory University（埃默里大学） ； Gradient Network ； University of Texas at Arlington（德克萨斯大学阿灵顿分校） ； University of Toronto（多伦多大学） 纠错

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

Position: Emergent Machina Sapiens Urge Rethinking Multi-Agent Paradigms

Hepeng Li, Yuhong Liu, Jun Yan, Jie Gao, Xiaoou Yang

机构 * University of Maine（缅因大学） ； Santa Clara University（圣克拉拉大学） ； Concordia University（Concordia大学） ； Delft University of Technology（代尔夫特理工大学） 纠错

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

MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework

Yifan Zhu, Chao Zhang, Xin Shi, Xueqiao Zhang, Yi Yang, Yawei Luo

机构 * Zhejiang University（浙江大学） 纠错

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

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models

Saaket Agashe, Yue Fan, Anthony Reyna, Xin Eric Wang

机构 * University of California Santa Cruz（加州大学圣克ruz分校） 纠错

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

An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework

Zeyu Wang, Frank P. -W. Lo, Qian Chen, Yongqi Zhang, Chen Lin, Xu Chen, Zhenhua Yu, Alexander J. Thompson, Eric M. Yeatman, Benny P. L. Lo

机构 * Imperial College London（帝国理工学院伦敦分校） ； Univeristy of Aberdeen（阿伯丁大学） 纠错

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

Comments Accepted by CVPR 2025 Workshop

Knowledge-Aware Iterative Retrieval for Multi-Agent Systems

Seyoung Song

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

Multi-Agent Image Restoration

Xu Jiang, Gehui Li, Bin Chen, Jian Zhang

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

Interactive Debugging and Steering of Multi-Agent AI Systems

Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney, Jack Gerrits, Erkang Zhu, Saleema Amershi

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

Comments Published at CHI 25

GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS

Saman Kazemkhani, Aarav Pandya, Daphne Cornelisse, Brennan Shacklett, Eugene Vinitsky

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

Comments ICLR 2025 camera-ready version

Journal ref ICLR 2025

VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework

He Kong, Die Hu, Jingguo Ge, Liangxiong Li, Tong Li, Bingzhen Wu

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

Leveraging Chemistry Foundation Models to Facilitate Structure Focused Retrieval Augmented Generation in Multi-Agent Workflows for Catalyst and Materials Design

Nathaniel H. Park, Tiffany J. Callahan, James L. Hedrick, Tim Erdmann, Sara Capponi

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

Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

Logan Cross, Violet Xiang, Agam Bhatia, Daniel LK Yamins, Nick Haber

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

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang, Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, Saleema Amershi

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

Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems

Alireza Ghafarollahi, Markus J. Buehler

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

KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models

Kemou Jiang, Xuan Cai, Zhiyong Cui, Aoyong Li, Yilong Ren, Haiyang Yu, Hao Yang, Daocheng Fu, Licheng Wen, Pinlong Cai

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

Comments 13 pages, 18 figures

LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments

Junzhe Chen, Xuming Hu, Shuodi Liu, Shiyu Huang, Wei-Wei Tu, Zhaofeng He, Lijie Wen

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

XUAT-Copilot: Multi-Agent Collaborative System for Automated User Acceptance Testing with Large Language Model

Zhitao Wang, Wei Wang, Zirao Li, Long Wang, Can Yi, Xinjie Xu, Luyang Cao, Hanjing Su, Shouzhi Chen, Jun Zhou

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

Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture

Sunil Kumar Jang Bahadur, Gopala Dhar

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

Comments Proposed workflow

AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering

AgentForge：用于学习智能体软件工程的沉浸式角色扮演平台

Zihan Fang, Yueke Zhang, Yu Huang

专题命中 多智能体 ：agentic(title,abstract)；agent(abstract)；AI agent(abstract)；planning(abstract)

AI总结 本研究提出沉浸式角色扮演平台AgentForge，让新手在多智能体代码修复工作流中担任软件工程角色，经37名新手开发者测试，该平台可提升新手的软件工程技能与智能体协作理解。

Comments 7 pages, 2 figures

ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment

ARCANE：一种多智能体框架，用于可解释和可配置的对齐

Charlie Masters, Marta Grześkiewicz, Stefano V. Albrecht

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；tool use(abstract)；分类 cs.AI、cs.CL

AI总结 ARCANE是一种多智能体框架，通过动态规则生成实现可解释和可配置的对齐，适用于复杂长期任务。

Comments Accepted to the AAAI 2026 LLAMAS Workshop (Large Language Model Agents for Multi-Agent Systems)

AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design

工程设计中的AI代理：一种用于汽车外观和空气动力学设计的多代理框架

Mohamed Elrefaie, Janet Qian, Raina Wu, Qian Chen, Angela Dai, Faez Ahmed

机构 * Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院机械工程系） ； Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院电气工程与计算机科学系） ； Department of Computer Science, Technical University of Munich, Munich, Germany（慕尼黑技术大学计算机科学系） 纠错

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

AI总结 本研究提出了一种多代理框架，利用AI代理提升汽车设计的美学和空气动力学性能，通过自动化任务加速设计流程。

Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code

Muhammad Haseeb

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.AI、cs.SE

Comments 15 pages, 5 figures, research paper on multi-agent LLM systems for code generation

Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi

F. Bredell, H. A. Engelbrecht, J. C. Schoeman

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

Comments This paper is accepted and published in the journal of autonomous agents and multi-agent systems (JAAMAS). The updated manuscript is the revised version after the final round of peer revision

Journal ref Autonomous Agents and Multi-agent Systems, vol. 39, no. 28, (2025)

Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications

Raphael Shu, Nilaksh Das, Michelle Yuan, Monica Sunkara, Yi Zhang

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

Comments Technical report for multi-agent collaboration on AWS Bedrock Agents

Deep Reinforcement Learning for Multi-Agent Interaction

Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht

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

Comments Published in AI Communications Special Issue on Multi-Agent Systems Research in the UK

AOC-CBS: Anytime-Optimal Continuous-time Conflict-Based Search for Generalised Multi-Agent Path Finding

AOC-CBS：适用于通用多智能体路径规划的任何时候最优连续时间基于冲突的搜索算法

Alvin Combrink, Sabino Francesco Roselli, Martin Fabian

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

AI总结 本研究针对通用多智能体路径规划问题，提出AOC-CBS算法，该算法可 anytime-optimal 求解，实验表明其在接受有界最优性间隙时能将可扩展性从数十智能体扩展到数百个。

Comments 65 pages, 19 figures

Optimal Multi-Agent Path Finding in Continuous Time

连续时间下的最优多智能体路径查找

Alvin Combrink, Sabino Francesco Roselli, Martin Fabian

机构 * Division of Systems and Control, Department of Electrical Engineering, Chalmers University of Technology（系统与控制系，电气工程系，查尔姆斯理工大学） 纠错

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

AI总结 本文针对CCBS类算法的精确性缺陷，提出满足充分条件的OC-CBS，可保证MAPFR实例的最优解，实验显示其运行时间与CCBS相当，还能恢复依赖CCBS的方法的理论保证。

Comments 41 pages, 23 figures

Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction

为何要研究涌现行为？你可以对其进行调控！让多智能体系统与奖励预测对齐

Assaf Caftory, Almog Zemach, Moshe Butman, Doron Friedman

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

AI总结 本文提出多智能体奖励预测（MARP）框架，通过学习共享奖励模型调控多智能体涌现行为，在收获游戏中验证其能使智能体行为对齐多样社会目标，为调控涌现行为提供了数据驱动的方法。