给大模型智能体的失败分类并自动修复，提升任务成功率。
Where LLM Agents Fail and How They can Learn From Failures
- 构建失败模式分类体系，按记忆、反思、规划等模块划分错误类型。
- 在ALFWorld等数据集上发现，修复后任务正确率提升24%，步级准确率提高17%。
- 提供针对性反馈，让智能体能自我修正，适合研究鲁棒性智能体的开发者。
大型语言模型（LLM）智能体通过整合规划、记忆、反思和工具使用模块，在解决复杂多步任务方面展现出潜力。然而其复杂架构也放大了级联失败的风险，即单个根源错误会传播至后续决策，导致任务失败。现有系统缺乏对智能体错误进行模块化与系统性理解的框架，难以有效检测此类错误。本文提出三项贡献：首先，构建AgentErrorTaxonomy，对记忆、反思、规划、动作及系统级操作等模块的失败模式进行分类；其次，创建AgentErrorBench，首个基于ALFWorld、GAIA和WebShop的真实智能体失败轨迹标注数据集；第三，提出AgentDebug调试框架，可定位根因错误并提供纠正反馈，使智能体实现恢复与迭代改进。在AgentErrorBench上的实验表明，AgentDebug相较最强基线，全正确率提升24%，步骤准确率提高17%。此外，定向反馈使智能体在任务成功率上相对提升最高达26%。这些结果确立了系统性调试作为提升LLM智能体可靠性与适应性的有效路径。代码与数据将公开于https://github.com/ulab-uiuc/AgentDebug。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions, leading to task failure. Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way, and therefore fail to detect these errors accordingly. We address this gap with three contributions. First, we introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations. Second, we construct AgentErrorBench, the first dataset of systematically annotated failure trajectories from ALFWorld, GAIA, and WebShop, grounding error analysis in real-world agent rollouts. Third, we propose AgentDebug, a debugging framework that isolates root-cause failures and provides corrective feedback, enabling agents to recover and iteratively improve. Experiments on AgentErrorBench show that AgentDebug achieves 24% higher all-correct accuracy and 17% higher step accuracy compared to the strongest baseline. Beyond detection, the targeted feedback generated by AgentDebug enables LLM agents to iteratively recover from failures, yielding up to 26% relative improvements in task success across ALFWorld, GAIA, and WebShop. These results establish principled debugging as a pathway to more reliable and adaptive LLM agents. The code and data will be available at https://github.com/ulab-uiuc/AgentDebug
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。