Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. Recently, researchers have further investigated Multi-Agent Debate (MAD) frameworks, which enhance the reasoning and collaboration capabilities of MAS through information exchange and debate among multiple agents. However, existing approaches often rely on unguided initialization, causing agents to adopt identical reasoning paths that lead to the same errors. As a result, effective debate among agents is hindered, and the final outcome frequently degenerates into simple majority voting. To solve the above problem, in this paper, we introduce Dynamic Multi-Agent Debate (DynaDebate), which enhances the effectiveness of multi-agent debate through three key mechanisms: (1) Dynamic Path Generation and Allocation, which employs a dedicated Path Generation Agent to generate diverse and logical solution paths with adaptive redundancy; (2) Process-Centric Debate, which shifts the focus from surface-level outcome voting to rigorous step-by-step logic critique to ensure process correctness; (3) A Trigger-Based Verification Agent, which is activated upon disagreement and uses external tools to objectively resolve deadlocks. Extensive experiments demonstrate that DynaDebate achieves superior performance across various benchmarks, surpassing existing state-of-the-art MAD methods.

翻译：近年来，基于大语言模型的多智能体系统（MAS）快速发展，在协同决策与复杂问题解决方面表现出色。研究者进一步探索了多智能体辩论（MAD）框架，通过多智能体间的信息交换与辩论来增强MAS的推理与协作能力。然而，现有方法通常依赖无引导的初始化，导致智能体采用相同的推理路径并产生相同错误。这阻碍了智能体间的有效辩论，最终结果往往退化为简单的多数表决。为解决上述问题，本文提出动态多智能体辩论框架（DynaDebate），通过三项关键机制提升多智能体辩论的效能：（1）动态路径生成与分配机制，采用专用的路径生成智能体来生成具有自适应冗余度的多样化逻辑解路径；（2）以过程为中心的辩论机制，将焦点从表层结果投票转向严格的逐步逻辑批判，以确保过程正确性；（3）基于触发的验证智能体，在出现分歧时激活，并借助外部工具客观解决僵局。大量实验表明，DynaDebate在多种基准测试中均取得优越性能，超越了现有最先进的多智能体辩论方法。