辩论者混合：在多智能体推理中实现架构级别的辩论学习
Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
AI总结：
提出Mixture of Debaters框架，通过混合专家范式在单一模型内实现动态自我辩论，解决静态架构和高计算开销问题，在多项基准上以更低延迟和令牌消耗取得更优性能。
摘要：
现有的多智能体辩论框架存在两个关键限制：它们依赖静态架构，其中智能体角色和协调模式在设计时固定；并且需要实例化多个模型副本，导致大量计算开销。我们提出辩论者混合（MoD），一个统一框架，通过利用混合专家范式在单一模型内实现动态自我辩论。我们解决了将MoE应用于辩证推理的三个关键挑战：（1）双路由，将角色分配与流程解耦，动态决定何时辩论与何时综合；（2）动量切换，通过局部上下文平滑令牌级路由，减少专家切换抖动；（3）统一自我辩论，将多样化的辩论角色封装为轻量级专家模块，消除智能体间通信同时保持行为多样性。在多模态基准上的大量实验表明，MoD优于单模型基线和传统多智能体系统，实现了更高的准确性，同时延迟降低3.7倍，令牌消耗减少87%。源代码可在https://github.com/YongLD/MoD获取。
英文摘要：
Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patterns are fixed at design time, and they require instantiating multiple model copies, incurring substantial computational overhead. We propose Mixture of Debaters (MoD), a unified framework that enables dynamic self-debate within a single model by leveraging the Mixture-of-Experts paradigm. We address three key challenges in adapting MoE for dialectical reasoning: (1) dual-routing that decouples role allocation from process flow, dynamically determining when to debate versus when to synthesize; (2) momentum switching that smooths token-level routing with local context, reducing expert-switch jitter; and (3) unified self-debate that encapsulates diverse debating personas into lightweight expert modules, eliminating inter-agent communication while preserving behavioral diversity. Extensive experiments on multimodal benchmarks demonstrate that MoD outperforms both single-model baselines and conventional multi-agent systems, achieving superior accuracy with 3.7x lower latency and 87% reduction in token consumption.The source code can be accessed at https://github.com/YongLD/MoD.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
