Autogram：用 LLM 为网络系统自动发现不变量
Invariant Discovery for Networked Systems
AI 导读
论文提出 Autogram，用 LLM 检查遥测变量元数据、分类计数器类型并归纳候选语法，再在该语法内做确定性统计搜索，迭代放宽语法直到恢复已知不变量。LLM 仅负责语法归纳，候选验证交给逻辑与统计检查，使 AI 提议转化为可审计、具形式保证的不变量。在公开和生产 WAN 遥测上，Autogram 以完全召回率和低假阳性恢复了专家推导的不变量。
正文 · 原文
Abstract:Invariants, the relations expected to hold among measured signals of a network, underpin applications from verification to traffic generation, telemetry imputation, and input validation. Yet, writing them by hand demands rare expertise in both formal logic and networking. Testing all possible combinations of telemetry variables statistically is intractable at network scale, while existing automatic tools still require a human-authored grammar of admissible invariants and learn only exact, "hard" rules that break under real-world noise. Our key idea is to use an LLM to inspect variable metadata, classify counter data types, and predict candidate syntactic relationships that form a compact grammar, followed by a deterministic statistical search within that grammar. If the initial grammar fails to recover trusted known invariants on held-out telemetry, Autogram instructs the LLM to iteratively widen the grammar until recovery succeeds. By confining the LLM to grammar induction and re-induction while delegating candidate verification to logical and statistical checks, Autogram turns non-deterministic AI proposals into auditable invariants with formal guarantees within the induced grammar. We design and prototype Autogram and evaluate it on both public and production WAN telemetry, recovering expert-derived invariants with full recall and low false positives. We close with a discussion of open problems on the path toward fully open-ended invariant discovery.
| Comments: | ACM HotNets 2026 |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Symbolic Computation (cs.SC) |
| MSC classes: | 68M15 (Primary), 68T27, 68T05 (Secondary) |
| ACM classes: | C.2.3; I.2.6; I.2.3 |
| Cite as: | arXiv:2607.22944 [cs.NI] |
| (or arXiv:2607.22944v2 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.22944 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3847290.3859952
DOI(s) linking to related resources |
Submission history
From: Hongyu Hè [view email]
[v1]
Fri, 24 Jul 2026 23:07:31 UTC (519 KB)
[v2]
Thu, 5 Nov 2026 00:15:25 UTC (306 KB)
来源：arXiv cs.AI · arxiv.org