It is shown that while fine-tuned LLMs excel at intent translation, they exhibit false negative rates when checking whether a proposed intent violates an existing security policy, and NetInspector is introduced, a three-layer agentic framework that enforces a verify-then-act protocol.
Abstract
Modern networks are large in scale and heterogeneous in configuration, making manual policy management increasingly impractical. Intent-Based Networking (IBN) addresses this by automating the translation of high-level operator goals into low-level network configurations. Yet existing IBN systems rely on static heuristics and fixed-feature classifiers that generalize poorly to distribution shifts such as new service definitions or evolving phrasing in operator requests. Large Language Models (LLMs), with strong reasoning and translation capabilities demonstrated across many domains, are a natural candidate for IBN policy generation. However, it is unclear whether LLMs can be reliably applied to this task, nor whether their use mitigates or worsens the underlying security risk. In this work, we show that while fine-tuned LLMs excel at intent translation, they exhibit false negative rates when checking whether a proposed intent violates an existing security policy. The root cause is not a lack of logical reasoning capability, but LLMs lack of persistent grounding in network topology and group hierarchy. Motivated by this finding, we introduce NetInspector, a three-layer agentic framework that enforces a verify-then-act protocol, decoupling information retrieval from reasoning so that the LLM focuses on symbolic reasoning while every policy decision is grounded in verifiable network facts retrieved from a live Environment Layer before approval. On NetInspector-Bench, a 2,224-sample synthetic benchmark spanning campus, enterprise, and WAN topologies, NetInspector reduces FNR by over 30\% relative to ungrounded baselines and remains robust under linguistic distribution shifts.
This work examines the degree to which an LLM's implicit representation of a finite-state transition system-defined via natural language descriptions-aligns with a manually generated ground-truth model.
An-Qi Chen, Dan Goldwasser, Cristina Nita-Rotaru· Conference on Empirical Meth...· 0 citations
Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large language model (LLM). Such systems, adopted in tools like Claude Code and Codex, remain vulnerable to failure modes such as scope escalation, wh...
Zhi-Xiong Zhuang, Jin Jia, Zhi-Wei Shang et al.· 1 citation
Intent-based networking decouples desired outcomes from device-level configuration, but most systems still map intents to parameters of an algorithm selected in advance. Large language models (LLMs) create an opportunity to automate algorithm design, yet unrestricted generated code is unsuitable for transport-network c...
Behnam Ojaghi, R. Vilalta, Raúl Muñoz· arXiv.org· 1 citation
Infrastructure as Code (IaC) enables the automated provisioning of cloud infrastructures, yet syntactically valid configurations may remain unsuitable for the applications they support. Addressing such issues requires knowledge of both the infrastructure and its runtime behavior. We introduce POLIAC, an LLM-based frame...
Haitam El Hayani, Jolan Philippe, Stéphanie Challita· Proceedings of the 3rd Inter...· 0 citations
Intent-based networking (IBN) promises QoS provisioning in which the network derives the configuration from operator-stated goals. Its first step, translating a natural-language intent into enforceable service-level objectives (SLOs) grounded in a live snapshot of the network state, increasingly relies on large languag...
Dynamic Retrieval-based Policy Generation (DRPG) is proposed, a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement.