# TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback

arXiv: https://arxiv.org/abs/2601.08734 · HTML: https://mlsanity.com/paper/2601.08734/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback](https://mlsanity.com/paper/2402.01391/) (2024)
- [SynCode: LLM Generation with Grammar Augmentation](https://mlsanity.com/paper/2403.01632/) (2024)
- [ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings](https://mlsanity.com/paper/2510.15681/) (2025)
- [A Survey of using Large Language Models for Generating Infrastructure as Code](https://mlsanity.com/paper/2404.00227/) (2024)
- [CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation](https://mlsanity.com/paper/2401.06786/) (2023)
- [Abstractions-of-Thought: Intermediate Representations for LLM Reasoning in Hardware Design](https://mlsanity.com/paper/2505.15873/) (2025)
- [Large Language Models for Unit Testing: A Systematic Literature Review](https://mlsanity.com/paper/2506.15227/) (2025)
- [Using a Feedback Loop for LLM-based Infrastructure as Code Generation](https://mlsanity.com/paper/2411.19043/) (2024)

## Built on by (most cited first, 5 of 5)

- [Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts](https://mlsanity.com/paper/2605.09055/) (2026)
- [Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code](https://mlsanity.com/paper/2605.09360/) (2026)
- [TerraRepair: A Tool-Grounded LLM Agent for Infrastructure-as-Code Repair](https://mlsanity.com/paper/2607.11390/) (2026)
- [Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation](https://mlsanity.com/paper/2608.02672/) (2026)
- [AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness](https://mlsanity.com/paper/2610.05367/) (2026)

## Abstract (arXiv)

Automating Infrastructure-as-Code (IaC) is challenging, and large language models (LLMs) often produce incorrect configurations from natural language (NL). We present TerraFormer, a neuro-symbolic framework for IaC generation and mutation that combines supervised fine-tuning with verifier-guided reinforcement learning, using formal verification tools to provide feedback on syntax, deployability, and policy compliance. We curate two large, high-quality NL-to-IaC datasets, TF-Gen (152k instances) and TF-Mutn (52k instances), via multi-stage verification and iterative LLM self-correction. Evaluations against 17 state-of-the-art LLMs, including ~50x larger models like Sonnet 3.7, DeepSeek-R1, and GPT-4.1, show that TerraFormer improves correctness over its base LLM by 15.94% on IaC-Eval, 11.65% on TF-Gen (Test), and 19.60% on TF-Mutn (Test). It outperforms larger models on both TF-Gen (Test) and TF-Mutn (Test), ranks third on IaC-Eval, and achieves top best-practices and security compliance.