Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.25370 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911184077193216 |
|---|---|
| author | Zhu, Kunlun Liu, Zijia Li, Bingxuan Tian, Muxin Yang, Yingxuan Zhang, Jiaxun Han, Pengrui Xie, Qipeng Cui, Fuyang Zhang, Weijia Ma, Xiaoteng Yu, Xiaodong Ramesh, Gowtham Wu, Jialian Liu, Zicheng Lu, Pan Zou, James You, Jiaxuan |
| author_facet | Zhu, Kunlun Liu, Zijia Li, Bingxuan Tian, Muxin Yang, Yingxuan Zhang, Jiaxun Han, Pengrui Xie, Qipeng Cui, Fuyang Zhang, Weijia Ma, Xiaoteng Yu, Xiaodong Ramesh, Gowtham Wu, Jialian Liu, Zicheng Lu, Pan Zou, James You, Jiaxuan |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25370 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Where LLM Agents Fail and How They can Learn From Failures Zhu, Kunlun Liu, Zijia Li, Bingxuan Tian, Muxin Yang, Yingxuan Zhang, Jiaxun Han, Pengrui Xie, Qipeng Cui, Fuyang Zhang, Weijia Ma, Xiaoteng Yu, Xiaodong Ramesh, Gowtham Wu, Jialian Liu, Zicheng Lu, Pan Zou, James You, Jiaxuan Artificial Intelligence 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 |
| title | Where LLM Agents Fail and How They can Learn From Failures |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.25370 |