AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Published in EMNLP 2026 (System Demonstration), 2026
AgentDebugX is an open-source debugging framework for LLM agents. It organizes debugging as a closed loop of Detect → Attribute → Recover → Rerun, with interfaces for live and offline trajectories.
Project website · GitHub repository
Recommended citation: Kunlun Zhu, Xuyan Ye, Zhiguang Han, Yuchen Zhao, Bingxuan Li, Weijia Zhang, Muxin Tian, Xiangru Tang, Pan Lu, James Zou, Jiaxuan You, and Heng Ji. (2026). "AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents." EMNLP 2026 (System Demonstration).
Download Paper