English(EN) VerifyMAS: Hypothesis Verification for Failure Attribution in LLM-based Multi-Agent Systems

VerifyMAS框架改进了LLM多智能体系统中的故障归因

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员推出VerifyMAS，一个新颖的假设验证框架，旨在改进大型语言模型驱动的多智能体系统（LLM-MAS）中的故障归因。该方法通过验证完整交互轨迹中的故障假设，而不是仅仅依赖于本地智能体日志，来解决现有方法的局限性。VerifyMAS有效捕捉全局故障，如跨步骤的不一致和智能体之间的协调错误，同时还减小了归因的组合搜索空间。实验表明，VerifyMAS提高了包括Qwen和GPT模型在内的各种LLM骨干的性能，在长多智能体轨迹的效率方面优于先前的方法。 AI

影响增强了复杂LLM驱动的多智能体系统的可靠性和调试能力。

排序理由该集群包含一篇详细介绍LLM驱动的多智能体系统新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM驱动的多智能体系统新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Hezhe Qiao, Hanghang Tong, Ee-Peng Lim, Bing Liu, Guansong Pang · 2026-10-27 04:00

VerifyMAS：基于LLM的多智能体系统中故障归因的假设验证

arXiv:2605.17467v2 Announce Type: replace Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing appro…

本文如何被排名

报道来源 [1]

VerifyMAS：基于LLM的多智能体系统中故障归因的假设验证

相关实体

相关话题