arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09341cs.AI
收藏

对多智能体大语言模型推理树进行审计优于多数投票和LLM作为裁判

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

University of Southern California, Los Angeles, CA, USA（美国南加州大学）

Wei Yang, Shixuan Li, Heng Ping, Peiyu Zhang, Paul Bogdan, Jesse Thomason

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

通过构建推理树路径搜索机制，AgentAuditor在多智能体系统中实现了优于多数投票和LLM作为裁判的推理准确性提升

摘要：

多智能体系统（MAS）可以显著扩展大型语言模型（LLMs）的推理能力，但大多数框架仍然使用多数投票来聚合智能体输出。这种启发式方法丢弃了推理轨迹的证据结构，并在共谋共识下容易崩溃，其中智能体分享相关偏见并收敛到相同的错误推理。我们引入了AgentAuditor，它用推理树上的路径搜索代替投票，该树明确表示智能体轨迹中的共识和分歧。AgentAuditor通过在关键分歧点比较推理分支来解决冲突，将全球裁决转化为高效的局部验证。我们进一步提出反共识偏好优化（ACPO），它在多数失败案例上训练裁决者，并奖励基于证据的少数选择而非流行错误。AgentAuditor对MAS设置无偏见，我们在5种流行的设置中发现，它在多数投票基础上提高了高达5%的绝对准确率，并在使用LLM作为裁判的基础上提高了高达3%。

英文摘要：

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

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。

↑