方差的价值：通过不确定性驱动的策略优化缓解多智能体系统中的辩论崩溃
The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
AI总结：
本文提出了一种基于不确定性驱动的策略优化方法，通过量化多智能体系统中的不确定性来缓解辩论崩溃问题，提升决策准确性和系统一致性。
摘要：
多智能体辩论（MAD）系统通过迭代辩论来提升大语言模型的推理能力，但仍然容易受到辩论崩溃的威胁，这是一种失败类型，其中最终智能体的决策因错误推理而受损。现有方法缺乏系统性的机制来检测或防止此类失败。为了解决这一缺口，我们首先提出一个分层指标，该指标在三个层次上量化行为不确定性：智能体内部（个体推理不确定性）、智能体之间（交互不确定性）以及系统层面（输出不确定性）。在多个基准上的实证分析表明，我们提出的不确定性量化能够可靠地指示系统故障，这证明了将其作为诊断指标来指示系统故障的有效性。随后，我们提出了一种缓解策略，通过制定不确定性驱动的策略优化，以惩罚自我矛盾、同伴冲突和低置信度输出，在动态辩论环境中进行优化。实验表明，我们提出的不确定性驱动的缓解策略能够有效校准多智能体系统，通过一致提高决策准确性并减少系统分歧来实现。
英文摘要：
Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack principled mechanisms to detect or prevent such failures. To address this gap, we first propose a hierarchical metric that quantifies behavioral uncertainty at three levels: intra-agent (individual reasoning uncertainty), inter-agent (interactive uncertainty), and system-level (output uncertainty). Empirical analysis across several benchmarks reveals that our proposed uncertainty quantification reliably indicates system failures, which demonstrates the validity of using them as diagnostic metrics to indicate the system failure. Subsequently, we propose a mitigation strategy by formulating an uncertainty-driven policy optimization to penalize self-contradiction, peer conflict, and low-confidence outputs in a dynamic debating environment. Experiments demonstrate that our proposed uncertainty-driven mitigation reliably calibrates the multi-agent system by consistently improving decision accuracy while reducing system disagreement.
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。
