一句话：多智能体系统 Holmes 利用多模态运行时信号，在无复现条件下对工业级混合语言移动崩溃做根因定位。
针对超大规模工业应用中混合语言移动崩溃难以本地复现、传统静态分析可扩展性差、既有 LLM 智能体依赖可复现环境的问题，本文提出多智能体系统 Holmes。它综合栈回溯、日志与线程状态等多模态运行时信号重建失败上下文，采用分层的 Retrieve-Explore-Reason 架构，并借助寄存器、汇编等底层工件弥合开源业务逻辑与闭源系统框架之间的语义鸿沟；同时利用运行时线索动态压缩搜索空间，在 7000 万行代码库中定位非局部缺陷。在微信真实崩溃上的评估显示，函数级故障定位准确率达 87.6%，平均排查时间减少逾 98%（约 77 秒），将劳动密集的调试转变为高效的验证流程。
Diagnosing mobile crashes in ultra-large-scale industrial applications is a formidable challenge due to the sheer volume of code, the complexity of mixed-language environments, and the inability to reproduce failures locally. Traditional static analysis struggles with scalability, while existing LLM-based agents often rely on reproducible environments unavailable in post-mortem scenarios. We present Holmes, a multi-agent system that automates root cause analysis by synthesizing multimodal runtime signals—stack traces, logs, and thread states—to reconstruct failure contexts without reproduction. Holmes introduces a hierarchical Retrieve-Explore-Reason architecture that leverages low-level artifacts (e.g., registers, assembly) to bridge the semantic gap between open-source business logic and closed-source system frameworks. By dynamically compressing the search space using runtime clues, Holmes precisely navigates 70-million-line codebases to identify non-local defects. Evaluated on real-world crashes from WeChat, Holmes achieves 87.6% accuracy in function-level fault localization and reduces average investigation time by over 98% (to ~77 seconds), demonstrating its effectiveness in transforming labor-intensive debugging into an efficient verification workflow.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2606-21963,
title = {Holmes: Multimodal Agentic Diagnosis for Mixed-Language Mobile Crashes at Industrial Scale},
author = {Jia Li and Wenyuan Ma and Ting Peng and Haibin Zheng and Yuetang Deng},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805212}
}