研究人员开发了一种名为OAT的新方法，用于LLM智能体系统的无监督故障归因。该方法通过学习成功的轨迹来识别推理时故障轨迹中的错误步骤，避免了昂贵的逐级标注。OAT利用神经控制微分方程对成功轨迹的动态进行建模，并为偏差步骤分配异常分数。实验表明，即使在训练数据有限的情况下，OAT也比现有的基于提示的方法更快、更准确。 AI
影响 这项研究提供了一种更有效、可扩展的调试LLM智能体的方法，有望加速其开发和部署。
排序理由 该集群包含一篇在arXiv上发表的研究论文，详细介绍了一种用于LLM智能体系统故障归因的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-ba…
Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which are computationally expensi…
Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which are computationally expensi…