AI Agent 犯错后，终于能自己找到病根了
AI Agent 出错时，表面报错的地方往往不是真正的原因，就像电脑蓝屏但问题出在几小时前装的软件。现有工具只能重放过程，不会帮你找根因。AgentDebugX 是一个开源调试框架，核心是 DeepDebug 模块：它先全局理解整个任务轨迹，再像侦探一样结构化排查，最后交叉验证。在 Who and When 基准上，它定位到具体 Agent 和步骤的准确率达 28.8%，比最强单次方法高 7 个百分点。在 GAIA 任务上，一次重跑就能修复 73 个失败任务中的 13 个，而其他自修复方法只能修 4-6 个。它提供 Python 库、命令行、网页控制台和可安装的 Agent 技能，还允许匿名分享调试案例作为社区记忆。这不是你明天就能用的工具，但它是让 AI Agent 从“会犯错”走向“会纠错”的关键一步。
📄 原文摘要(英文)
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but provide little support for identifying the root cause or translating diagnosis into recovery. We present AgentDebugX, an open-source debugging framework that organizes debugging as a closed loop of Detect, Attribute, Recover, and Rerun. At its core, DeepDebug performs multi-turn root-cause diagnosis through global trajectory understanding, structure-guided investigation, and cross-examination. On the Who and When benchmark, DeepDebug achieves the best strict attribution accuracy among the evaluated methods on both tested open-weight backbones, reaching 28.8 percent exact agent-and-step accuracy on qwen3.5-9b versus 21.7 percent for the strongest single-pass baseline. On GAIA, DeepDebug repairs 13 of 73 failed tasks in a single rerun, compared with 4 to 6 for three decoupled self-correction baselines, improving overall accuracy from 55.8 percent to 63.6 percent. AgentDebugX exposes this workflow through a Python library, CLI, web console, and installable agentic skill, and provides an opt-in Error Hub for sharing scrubbed failure-diagnosis-repair bundles and reusing them as debugging memory.