# On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software

arXiv: https://arxiv.org/abs/2504.02141 · HTML: https://mlsanity.com/paper/2504.02141/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)

## Builds on (most cited first, 25 of 25)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [Language-Guided Traffic Simulation via Scene-Level Diffusion](https://mlsanity.com/paper/2306.06344/) (2023)
- [Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning](https://mlsanity.com/paper/2207.08281/) (2022)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- [Using Large Language Models to Generate JUnit Tests: An Empirical Study](https://mlsanity.com/paper/2305.00418/) (2023)
- [LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs](https://mlsanity.com/paper/2312.04372/) (2023)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [In-IDE Code Generation from Natural Language: Promise and Challenges](https://mlsanity.com/paper/2101.11149/) (2021)
- [Fully Autonomous Programming with Large Language Models](https://mlsanity.com/paper/2304.10423/) (2023)
- [LangProp: A code optimization framework using Large Language Models applied to driving](https://mlsanity.com/paper/2401.10314/) (2024)
- [Engineering Safety Requirements for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2403.16289/) (2024)
- [Requirements Engineering using Generative AI: Prompts and Prompting Patterns](https://mlsanity.com/paper/2311.03832/) (2023)
- [Software Testing of Generative AI Systems: Challenges and Opportunities](https://mlsanity.com/paper/2309.03554/) (2023)
- [Ethical Interviews in Software Engineering](https://mlsanity.com/paper/1906.07993/) (2019)
- [An Industrial Experience Report about Challenges from Continuous Monitoring, Improvement, and Deployment for Autonomous Driving Features](https://mlsanity.com/paper/2403.09474/) (2024)
- [Correlation of Software-in-the-Loop Simulation with Physical Testing for Autonomous Driving](https://mlsanity.com/paper/2406.03040/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Survey of GenAI for Automotive Software Development: From Requirements to Executable Code](https://mlsanity.com/paper/2507.15025/) (2025)
- [Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations](https://mlsanity.com/paper/2608.16970/) (2026)

## Abstract (arXiv)

Automated Driving System (ADS) is a safety-critical software system responsible for the interpretation of the vehicle's environment and making decisions accordingly. The unbounded complexity of the driving context, including unforeseeable events, necessitate continuous improvement, often achieved through iterative DevOps processes. However, DevOps processes are themselves complex, making these improvements both time- and resource-intensive. Automation in code generation for ADS using Large Language Models (LLM) is one potential approach to address this challenge. Nevertheless, the development of ADS requires rigorous processes to verify, validate, assess, and qualify the code before it can be deployed in the vehicle and used. In this study, we developed and evaluated a prototype for automatic code generation and assessment using a designed pipeline of a LLM-based agent, simulation model, and rule-based feedback generator in an industrial setup. The LLM-generated code is evaluated automatically in a simulation model against multiple critical traffic scenarios, and an assessment report is provided as feedback to the LLM for modification or bug fixing. We report about the experimental results of the prototype employing Codellama:34b, DeepSeek (r1:32b and Coder:33b), CodeGemma:7b, Mistral:7b, and GPT4 for Adaptive Cruise Control (ACC) and Unsupervised Collision Avoidance by Evasive Manoeuvre (CAEM). We finally assessed the tool with 11 experts at two Original Equipment Manufacturers (OEMs) by conducting an interview study.