通过保留最多样化的观点，减少冗余信息，提升多智能体辩论效率。
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
- 基于多样性筛选机制，只广播最具分歧的对话内容
- 在多个基准上提升推理表现，尤其在智能体数量增多时优势明显
- 适合追求高效、高质量多智能体推理的开发者与研究者
多智能体辩论作为提升大语言模型推理质量的新兴框架，依赖智能体间迭代通信。然而每轮广播所有消息会引入噪声和冗余，降低辩论质量并浪费算力。现有方法依赖置信度估计过滤低置信响应，但因置信分数校准不准且对阈值敏感而不可靠。为此，我们提出多样性感知保留（DAR），每轮选择与多数意见及彼此差异最大的一组响应进行广播。通过显式的索引保留机制，DAR不修改原始消息，确保分歧的真实性。在多样化推理与问答基准上的实验表明，该选择性传播策略显著提升辩论性能，尤其在智能体数量增加时噪声累积最严重的情况下效果更优。结果表明，在多智能体推理系统中，‘听’的内容与‘说’的内容同等重要。代码已公开于 https://github.com/DA2I2-SLM/DAR。
原文摘要 · Abstract (English)
Multi-Agent Debate has emerged as a promising framework for improving the reasoning quality of large language models through iterative inter-agent communication. However, broadcasting all agent messages at every round introduces noise and redundancy that can degrade debate quality and waste computational resources. Current approaches rely on uncertainty estimation to filter low-confidence responses before broadcasting, but this approach is unreliable due to miscalibrated confidence scores and sensitivity to threshold selection. To address this, we propose Diversity-Aware Retention (DAR), a lightweight debate framework that, at each debate round, selects the subset of agent responses that maximally disagree with each other and with the majority vote before broadcasting. Through an explicit index-based retention mechanism, DAR preserves the original messages without modification, ensuring that retained disagreements remain authentic. Experiments on diverse reasoning and question answering benchmarks demonstrate that our selective message propagation consistently improves debate performance, particularly as the number of agents scales, where noise accumulation is most severe. Our results highlight that what agents hear is as important as what agents say in multi-agent reasoning systems. Code is publicly available at https://github.com/DA2I2-SLM/DAR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。