认知增益,偶然成本:多智能体辩论中的不确定性分解用于数学推理
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
AI总结:
本文提出贝叶斯不确定性分析框架,将多智能体辩论中的预测不确定性分解为认知不确定性和偶然不确定性,并设计不确定性引导的多智能体强化学习算法,在控制偶然成本的同时提升认知增益,从而提高推理准确性和辩论效率。
摘要:
多智能体辩论(MAD)在改善推理和减少幻觉方面显示出前景,但信息交换如何塑造个体推理行为仍不清楚。经验上,MAD表现出矛盾现象,包括准确率随token熵增加而上升,以及同质和异质智能体组合之间的显著差异。在本文中,我们引入了一个用于MAD的贝叶斯不确定性分析框架,该框架将答案级别的预测不确定性分解为认知不确定性和偶然不确定性,分别对应辩论的潜在增益和成本。在多种智能体配置下,我们发现有效的辩论取决于在受控的偶然成本下实现高认知增益。基于这一见解,我们设计了一种不确定性引导的多智能体强化学习算法,鼓励更低的偶然成本和更有效的认知信息利用。实验表明,我们的方法同时提高了每个智能体的准确性,并促进了更富有成效的辩论过程,为理解和改进MAD提供了一个可操作的贝叶斯视角。
英文摘要:
Multi-Agent Debate (MAD) has shown promise in improving reasoning and reducing hallucinations, yet it remains unclear how information exchange shapes individual reasoning behavior. Empirically, MAD exhibits paradoxical phenomena, including rising accuracy with increasing token entropy and marked differences between homogeneous and heterogeneous agent combinations. In this paper, we introduce a Bayesian uncertainty analysis framework for MAD, which decomposes answer-level predictive uncertainty into epistemic uncertainty and aleatoric uncertainty, corresponding to the potential gain and cost of debate. Across multiple agent configurations, we find that effective debate depends on achieving high epistemic gain under controlled aleatoric cost. Building on this insight, we design an uncertainty-guided multi-agent reinforcement learning algorithm that encourages lower aleatoric cost and more effective epistemic information utilization. Experiments show that our approach simultaneously enhances each agent's accuracy and promotes a more productive debate process, providing an operational Bayesian perspective for understanding and improving MAD.
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。