Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains unclear. We study these mechanisms using an AutoGen-based multi-agent framework for linear-elastic Finite Element Analysis (FEA), evaluating seven role configurations across four tasks under a fixed 12-turn conversation limit. From 1,120 controlled trials, we find that collaboration effectiveness depends more on functional complementarity than team size: the three-agent Coder-Executor-Critic configuration uniquely produced physically and visually correct solutions, while adding redundant reviewers reduced success rates. Yet three systematic failure modes persist: (1) affirmation bias, where the Rebuttal agent endorsed rather than challenged outputs (85-92% agreement, including errors); (2) premature consensus caused by redundant reviewers; and (3) a verification-validation gap where executable but physically incorrect code passed undetected. No agent combination successfully validated constitutive relations in complex tasks. Building on theories of functional diversity, role differentiation, and computational validation, we propose actionable design principles: (i) assign complementary agent roles, (ii) enforce multi-level validation (execution, specification, physics), and (iii) prevent early consensus through adversarial or trigger-based interaction control. These findings establish a principled foundation for designing trustworthy LLM collaborations in engineering workflows.
Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration
Shenzhen International Graduate School, Tsinghua University(深圳国际研究生院,清华大学);Huawei Tenchnologies Co., Ltd.(华为技术有限公司);University of Science and Technology of China(中国科学技术大学)
AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering
University of Houston(休斯顿大学);New York University(纽约大学);Texas A&M University(德克萨斯农工大学);UCSD(加州大学圣地亚哥分校);Worcester Polytechnic Institute(伍斯特理工学院);Oregon State University(俄勒冈州立大学)
The Athenian Academy: A Seven-Layer Architecture Model for Multi-Agent Systems
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Tianjin Academy of Fine Arts(天津美术学院);Central Academy of Fine Arts(中央美术学院);WaytoAGI
Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Faculty of Data Science, City University of Macau(数据科学学院,澳门城市大学);Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)(计算能力网络与信息安全重点实验室,教育部,山东计算机科学中心,齐鲁工业大学(山东科学院));Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science(山东省计算能力互联网与服务计算重点实验室,山东省计算机科学基础研究中心)
Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
Peking University(北京大学);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学);Siemens(西门子);Tencent Robotics X(腾讯机器人实验室)
Multi-Agent Collaboration via Evolving Orchestration
Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Beijing University of Posts and Telecommunications(北京邮电大学);Siemens(西门子);Tencent Robotics X(腾讯机器人研究院)
AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
University of Virginia(弗吉尼亚大学);Arizona State University(亚利桑那州立大学);University of Minnesota Twin Cities(明尼苏达大学双城分校);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions
School of Cyber Science and Engineering(网络科学与工程学院);Xi'an Jiaotong University(西安交通大学);School of Mechatronic Engineering and Automation(机械电子工程与自动化学院);Shanghai University(上海大学)
MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration
Queen Mary University of London(伦敦玛丽女王大学);Duke Kunshan University(昆山杜克大学);Hong Kong University of Science and Technology(香港科技大学);School of Engineering, Westlake University(西湖大学工学院);Research Center for Industries of the Future, Westlake University(西湖大学未来产业研究中心)
Multi-Agent Collaboration via Reward Attribution Decomposition
University of California, Berkeley(加州大学伯克利分校);Unveristy of California, San Diego(加州大学圣地亚哥分校);Tsinghua University(清华大学);Facebook AI Research(Facebook人工智能研究院)