arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.04886cs.AIcs.MA
收藏

哪里出了问题?多智能体错误归因的层级视角

Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution

Amazon Web Services(亚马逊网络服务)

Adi Banerjee, Anirudh Nair, Tarik Borogovac

AI总结:

本文提出ECHO算法,通过层级上下文表示、目标分析与共识投票,解决LLM多智能体系统中的错误归因难题,实验证明其在复杂交互场景中优于现有方法。

摘要:

在大语言模型(LLM)多智能体系统中,错误归因在调试和改进协作式AI系统方面提出了重大挑战。当前用于定位交互轨迹中智能体和步骤级故障的方法——无论是采用一次性整体评估、逐步分析还是二分搜索——在分析复杂模式时均显不足,在准确性和一致性方面均存在困难。我们提出了ECHO(通过上下文层级与目标共识分析进行错误归因),这是一种新颖的算法,它结合了层级上下文表示、基于目标分析的评价以及共识投票,以提高错误归因的准确性。我们的方法利用基于位置的上下文理解分层,同时保持客观的评价标准,最终通过共识机制得出结论。实验结果表明,ECHO在多种多智能体交互场景中优于现有方法,在涉及细微推理错误和复杂相互依赖的情况下表现出特别强的优势。我们的研究结果表明,利用结构化、层级化上下文表示的概念,并结合基于共识的客观决策,为多智能体系统中的错误归因提供了一个更稳健的框架。

英文摘要:

Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces - whether using all-at-once evaluation, step-by-step analysis, or binary search - fall short when analyzing complex patterns, struggling with both accuracy and consistency. We present ECHO (Error attribution through Contextual Hierarchy and Objective consensus analysis), a novel algorithm that combines hierarchical context representation, objective analysis-based evaluation, and consensus voting to improve error attribution accuracy. Our approach leverages a positional-based leveling of contextual understanding while maintaining objective evaluation criteria, ultimately reaching conclusions through a consensus mechanism. Experimental results demonstrate that ECHO outperforms existing methods across various multi-agent interaction scenarios, showing particular strength in cases involving subtle reasoning errors and complex interdependencies. Our findings suggest that leveraging these concepts of structured, hierarchical context representation combined with consensus-based objective decision-making, provides a more robust framework for error attribution in multi-agent systems.

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。

↑