通过量化不确定性提升多智能体辩论系统的可靠性
The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
- 从个体、交互到系统三层量化推理不确定性
- 降低错误推理导致的决策崩溃，准确率显著提升
- 适合研究大模型协同推理与容错机制的学者
多智能体辩论（MAD）系统通过迭代讨论提升大语言模型的推理能力，但仍易出现辩论崩溃——即最终决策因错误推理而失效。现有方法缺乏可解释的故障检测与预防机制。本文提出一种分层不确定性度量，从个体推理、智能体间互动和系统输出三个层面量化行为不确定性。在多个基准上的实证分析表明，该度量能可靠指示系统故障，验证了其作为诊断指标的有效性。进一步提出基于不确定性的策略优化方法，在动态辩论环境中惩罚自我矛盾、同伴冲突和低置信度输出。实验显示，该方法能有效校准多智能体系统，持续提升决策准确率并减少系统内意见分歧。
原文摘要 · Abstract (English)
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.
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。