# What do LLMs need to Synthesize Correct Router Configurations?

arXiv: https://arxiv.org/abs/2307.04945 · HTML: https://mlsanity.com/paper/2307.04945/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2023.

## Built on by (most cited first, 29 of 29)

- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [Clover: Closed-Loop Verifiable Code Generation](https://mlsanity.com/paper/2310.17807/) (2023)
- [TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models](https://mlsanity.com/paper/2407.09424/) (2024)
- [Can Large Language Models Find And Fix Vulnerable Software?](https://mlsanity.com/paper/2308.10345/) (2023)
- [Large Language Models for Networking: Workflow, Advances and Challenges](https://mlsanity.com/paper/2404.12901/) (2024)
- [GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration](https://mlsanity.com/paper/2407.08249/) (2024)
- [MoE2: Optimizing Collaborative Inference for Edge Large Language Models](https://mlsanity.com/paper/2501.09410/) (2025)
- [Man-Made Heuristics Are Dead. Long Live Code Generators!](https://mlsanity.com/paper/2510.08803/) (2025)
- [INTA: Intent-Based Translation for Network Configuration with LLM Agents](https://mlsanity.com/paper/2501.08760/) (2025)
- [TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving](https://mlsanity.com/paper/2506.10674/) (2025)
- [Mapping the Landscape of Generative AI in Network Monitoring and Management](https://mlsanity.com/paper/2502.08576/) (2025)
- [FastRAG: Retrieval Augmented Generation for Semi-structured Data](https://mlsanity.com/paper/2411.13773/) (2024)
- [Robust Heuristic Algorithm Design with LLMs](https://mlsanity.com/paper/2510.08755/) (2025)
- [An LLM-based Agentic Framework for Accessible Network Control](https://mlsanity.com/paper/2509.20600/) (2025)
- [Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety](https://mlsanity.com/paper/2605.12729/) (2026)
- [From Connectivity to Autonomy: The Dawn of Self-Evolving Communication Systems](https://mlsanity.com/paper/2505.23710/) (2025)
- [Understanding Network Behaviors through Natural Language Question-Answering](https://mlsanity.com/paper/2510.21894/) (2025)
- [TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications](https://mlsanity.com/paper/2601.00691/) (2026)
- [Advanced LLM-Enhanced Intent-Based 5G Network Management using Dynamic Semantic Routes](https://mlsanity.com/paper/2608.22644/) (2026)
- [NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration](https://mlsanity.com/paper/2608.23179/) (2026)
- [Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization](https://mlsanity.com/paper/2609.04486/) (2026)
- [Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks](https://mlsanity.com/paper/2409.19007/) (2024)
- [BEAR: BGP Event Analysis and Reporting](https://mlsanity.com/paper/2506.04514/) (2025)
- [Automated Network Protocol Testing with LLM Agents](https://mlsanity.com/paper/2510.13248/) (2025)
- [Aether: Network Validation Using Agentic AI and Digital Twin](https://mlsanity.com/paper/2604.18233/) (2026)
- [Can AI Agents Detect and Repair Artifact Drift in Network Experiments?](https://mlsanity.com/paper/2609.09849/) (2026)
- [Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?](https://mlsanity.com/paper/2609.10181/) (2026)
- [Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems](https://mlsanity.com/paper/2609.16599/) (2026)
- [Can You Check That? The Checkability Boundary for Local LLM Network Automation](https://mlsanity.com/paper/2609.31540/) (2026)

## Abstract (arXiv)

We investigate whether Large Language Models (e.g., GPT-4) can synthesize correct router configurations with reduced manual effort. We find GPT-4 works very badly by itself, producing promising draft configurations but with egregious errors in topology, syntax, and semantics. Our strategy, that we call Verified Prompt Programming, is to combine GPT-4 with verifiers, and use localized feedback from the verifier to automatically correct errors. Verification requires a specification and actionable localized feedback to be effective. We show results for two use cases: translating from Cisco to Juniper configurations on a single router, and implementing no-transit policy on multiple routers. While human input is still required, if we define the leverage as the number of automated prompts to the number of human prompts, our experiments show a leverage of 10X for Juniper translation, and 6X for implementing no-transit policy, ending with verified configurations.