大型语言模型（LLMs）表现出强大的性能，但往往缺乏可解释的推理。本文介绍了面向多样化思维模式的多智能体协作框架（Multi-Agent Collaboration Framework for Diverse Thinking Modes，DiMo），该框架通过模拟四个专业化 LLM 智能体之间的结构化辩论，同时提升性能与可解释性。每个智能体体现一种不同的推理范式，使该框架能够协作探索多样化的认知方法。通过迭代辩论，智能体对初始回答提出质疑并加以完善，从而产生更稳健的结论以及明确、可审计的推理链。在六个基准测试上并在统一的开源设置下，DiMo 相比广泛使用的单模型和辩论基线提高了准确率，其中在数学方面取得最大增益。我们将 DiMo 定位为一个语义感知、Web 原生的多智能体框架：它利用 LLM 智能体对人机智能进行建模，这些智能体生成带有语义类型和 URL 标注的证据链，用于解释和用户友好的交互。尽管我们的实验使用标准推理基准，但该框架被设计为可在 Web 语料库和知识图谱之上实例化，将检索增强推理与下游系统可检查和复用的结构化论证相结合。
英文摘要：
Large Language Models (LLMs) demonstrate strong performance but often lack interpretable reasoning. This paper introduces the Multi-Agent Collaboration Framework for Diverse Thinking Modes (DiMo), which enhances both performance and interpretability by simulating a structured debate among four specialized LLM agents. Each agent embodies a distinct reasoning paradigm, allowing the framework to collaboratively explore diverse cognitive approaches. Through iterative debate, agents challenge and refine initial responses, yielding more robust conclusions and an explicit, auditable reasoning chain. Across six benchmarks and under a unified open-source setup, DiMo improves accuracy over widely used single-model and debate baselines, with the largest gains on math. We position DiMo as a semantics-aware, Web-native multi-agent framework: it models human-machine intelligence with LLM agents that produce semantically typed, URL-annotated evidence chains for explanations and user-friendly interactions. Although our experiments use standard reasoning benchmarks, the framework is designed to be instantiated over Web corpora and knowledge graphs, combining retrieval-augmented reasoning with structured justifications that downstream systems can inspect and reuse.
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
Shanghai Institute of AI for Education（上海人工智能教育研究院）；School of Computer Science（计算机科学学院）；East China Normal University（东华大学）；Tencent Inc.（腾讯公司）；Shanghai Innovation Institute（上海创新研究院）
Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team
East China Normal University（华东师范大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）；Bytedance Inc（字节跳动）；Canadian Collaborative Entrepreneurs Organization Inc（加拿大合作企业家组织）
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of British Columbia（不列颠哥伦比亚大学）；University College London（伦敦大学学院）
Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
Informatics, University of Illinois Urbana-Champaign（信息学，伊利诺伊大学厄巴纳-香槟分校）；Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign（Siebel 计算与数据科学学院，伊利诺伊大学厄巴纳-香槟分校）；Department of Computer Science, University of Toronto（计算机科学系，多伦多大学）；Allen Institute for AI（人工智能研究院）；School of Information Sciences, University of Illinois at Urbana-Champaign（信息科学学院，伊利诺伊大学厄巴纳-香槟分校）
When LLMs Team Up: The Emergence of Collaborative Affective Computing
Department of Computing, Hong Kong Polytechnic University（香港理工大学计算机系）；School of Data Science, Lingnan University（岭南大学数据科学学院）；School of Computer Science and the Data Science Institute, University of Technology Sydney（悉尼大学计算机科学学院和数据科学研究所）；Education University of Hong Kong（香港教育大学）
School of Informatics, Xiamen University, China（厦门大学信息学院）；Department of Digital Media Technology, Xiamen University, China（厦门大学数字媒体技术系）；Baidu Inc., Beijing, China（百度公司）
Assessing and Understanding Creativity in Large Language Models
University of Science and Technology of China（中国科学技术大学）；Chinese Academy of Sciences（中国科学院）；Shanghai Innovation Center for Processor Technologies（上海处理器技术创新中心）；University of Chinese Academy of Sciences（中国科学院大学）
Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning
Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Department of Language Science and Technology, Hong Kong Polytechnic University（香港理工大学语言科学与技术系）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院）；School of Data Science, Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；School of Artificial Intelligence, Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）
