让AI辩论时表达信心，提升多智能体系统决策效果
Enhancing Multi-Agent Debate System Performance via Confidence Expression
- 在多智能体辩论中引入显式信心表达机制
- 实验表明信心表达显著提升系统整体性能
- 适合关注AI协作与决策优化的研究者
生成式大语言模型（LLMs）在多项任务中表现卓越。近期研究提出多智能体辩论（MAD）系统，通过多个LLMs模拟人类辩论以提升任务表现。然而，尽管某些LLMs在特定任务中具备更优知识或推理能力，却常难以清晰传达此优势，部分原因在于缺乏信心表达。不当的信心表达可能导致智能体固执坚持错误观点或过早收敛至次优答案，从而降低辩论有效性与系统整体性能。为此，我们提出在MAD系统中引入信心表达，使LLMs能明确传递其信心水平。为验证该方法，我们构建了ConfMAD框架，将信心表达融入整个辩论流程。实验结果证明该方法有效，并进一步分析了信心对辩论动态的影响，为设计具备信心感知能力的MAD系统提供洞见。
原文摘要 · Abstract (English)
Generative Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Recent research has introduced Multi-Agent Debate (MAD) systems, which leverage multiple LLMs to simulate human debate and thereby improve task performance. However, while some LLMs may possess superior knowledge or reasoning capabilities for specific tasks, they often struggle to clearly communicate this advantage during debates, in part due to a lack of confidence expression. Moreover, inappropriate confidence expression can cause agents in MAD systems to either stubbornly maintain incorrect beliefs or converge prematurely on suboptimal answers, ultimately reducing debate effectiveness and overall system performance. To address these challenges, we propose incorporating confidence expression into MAD systems to allow LLMs to explicitly communicate their confidence levels. To validate this approach, we develop ConfMAD, a MAD framework that integrates confidence expression throughout the debate process. Experimental results demonstrate the effectiveness of our method, and we further analyze how confidence influences debate dynamics, offering insights into the design of confidence-aware MAD systems.
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。