发表机构
University of Illinois（伊利诺伊大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对多智能体系统故障归因任务，提出轻量级图框架AFANet，其参数少、推理成本低，在域内基准上性能匹配或优于LLM基线，分布外基准可经低成本自适应提升，证明轻量级结构化方法可实现优异故障归因效果。
AI 中文摘要
基于大语言模型（LLM）的多智能体系统（MAS）常表现出复杂的故障模式，导致智能体产生错误结果，这催生了智能体故障归因任务：给定一条失败的多智能体轨迹，识别出故障智能体及其对应的错误类型。现有方法主要依赖LLM完成故障归因，方式包括直接提示、在合成数据上微调或复杂的智能体流水线。这些方法虽有效，但因长上下文处理、昂贵的后训练及手工工作流产生大量计算开销；且经验证据表明，即便最先进的模型在现有基准上准确率也有限，仅靠扩大模型规模不足。本研究重新审视该任务，质疑此类昂贵生成式解决方案的必要性，引入AFANet这一轻量级图框架，通过步骤级语义信号与智能体级关系对交互轨迹建模。结果显示，AFANet参数显著更少、推理成本近乎为零，在域内基准上可匹配或优于包括微调模型在内的LLM基线，在不同图神经网络（GNN）架构间表现稳健，且在分布外（OOD）基准上通过低成本测试时自适应可进一步提升性能。研究表明，有效的智能体故障归因无需重型LLM推理，轻量级结构化方法即可实现优异性能。
英文摘要
Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task of Agent Failure Attribution: given a failed multi-agent trajectory, identify the faulty agents and their corresponding error types. Existing approaches predominantly rely on LLMs to perform failure attribution, either through direct prompting, fine-tuning on synthetic data or complex agentic pipelines. While effective, these methods incur substantial computational overhead due to long-context processing, expensive post-training and handcrafted workflows. Moreover, empirical evidence shows that even state-of-the-art models achieve limited accuracy on existing benchmarks, suggesting that scaling model size alone is insufficient. In this work, we revisit this task and question the necessity of such expensive generative solutions. We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships. We show that with significantly fewer parameters and near-zero inference cost, AFANet (i) matches or outperforms LLM-based baselines, including fine-tuned models on in-domain benchmarks, (ii) maintains robust performance across different GNN architectures and (iii) can be further improved with inexpensive test-time adaptation on the OOD benchmark. Our results suggest that effective agent failure attribution does not require heavy LLM reasoning and a lightweight, structured approach can achieve strong performance.
