arXiv cs.AI· Sayan Sinha, Vipul Harsh, B. Aditya Prakash, Vyas Sekar, Hui Zhang·· 10 天前AI 评分24
E4：用受限 DSL 实现互联网级服务智能体根因分析
Agentic RCA for Internet-Scale Services Using Constrained Creativity
AI 导读
针对互联网级服务故障排查，研究者提出智能体系统 E4，通过受限 DSL 让 LLM 智能体生成无循环数据流程序而非任意代码，兼顾准确性与可解释性。在合成与真实混合负载上，E4 准确率最高提升 62%，成本最多降低 12 倍，同时输出更可解释的响应。
正文 · 原文
Abstract:System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubleshooting system to be: (1) expressive to known and unknown incidents with high accuracy; (2) cost efficient at scale; (3) explainable to provide actionable insights operators can act on; and (4) entail low effort from the operators. Unfortunately, most existing systems, including emerging LLM-assisted agentic workflows and structured frameworks for authoring diverse RCA algorithms fall short of achieving all four requirements. We present E4, a novel agentic system for troubleshooting for Internet-scale services. E4 embodies the paradigm of constrained creativity that combines the best of LLM-assisted automation and exploration with the explainability and efficiency of a structured approach. Instead of allowing an LLM agent to write arbitrary code or generate arbitrary responses, we provide the agent a restricted DSL to generate its response via simple loop-free data flow programs. This DSL, equipped with high level operators for troubleshooting, makes E4's output accurate, verifiable and explainable. On a mix of synthetic and real-world workloads, E4 achieves up to 62% better accuracy compared to state-of-the-art solutions, while providing more explainable responses at up to 12x reduced cost.
| Comments: | 21 pages, including the references and appendix; 10 figures; 4 tables |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08622 [cs.NI] |
| (or arXiv:2610.08622v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08622 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sayan Sinha [view email]
[v1]
Tue, 6 Oct 2026 16:21:57 UTC (665 KB)
来源：arXiv cs.AI · arxiv.org