# LangProp: A code optimization framework using Large Language Models applied to driving

arXiv: https://arxiv.org/abs/2401.10314 · HTML: https://mlsanity.com/paper/2401.10314/

## Key facts

- Cited by 18 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 42 of its 59 references that are in the map.
- First posted on arXiv 18 Jan 2024.

## 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, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [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)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)

## Built on by (most cited first, 18 of 18)

- [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025)
- [Hidden Biases of End-to-End Driving Datasets](https://mlsanity.com/paper/2412.09602/) (2024)
- [LLMs: A Game-Changer for Software Engineers?](https://mlsanity.com/paper/2411.00932/) (2024)
- [LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends](https://mlsanity.com/paper/2410.15281/) (2024)
- [Generating and Evolving Reward Functions for Highway Driving with Large Language Models](https://mlsanity.com/paper/2406.10540/) (2024)
- [Learning Game-Playing Agents with Generative Code Optimization](https://mlsanity.com/paper/2508.19506/) (2025)
- [Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective](https://mlsanity.com/paper/2508.01443/) (2025)
- [Survey of GenAI for Automotive Software Development: From Requirements to Executable Code](https://mlsanity.com/paper/2507.15025/) (2025)
- [A Survey on Large Language Model-empowered Autonomous Driving](https://mlsanity.com/paper/2409.14165/) (2024)
- [On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software](https://mlsanity.com/paper/2504.02141/) (2025)
- [PerfCoder: Large Language Models for Interpretable Code Performance Optimization](https://mlsanity.com/paper/2512.14018/) (2025)
- [CktEvo: Repository-Level RTL Code Benchmark for Design Evolution](https://mlsanity.com/paper/2603.08718/) (2026)
- [LLM-based Realistic Safety-Critical Driving Video Generation](https://mlsanity.com/paper/2507.01264/) (2025)
- [IndustryCode: A Benchmark for Industry Code Generation](https://mlsanity.com/paper/2604.02729/) (2026)
- [On Debiasing Text Embeddings Through Context Injection](https://mlsanity.com/paper/2410.12874/) (2024)
- [AI-CDA4All: Democratizing Cooperative Autonomous Driving for All Drivers via Affordable Dash-cam Hardware and Open-source AI Software](https://mlsanity.com/paper/2505.06749/) (2025)
- [The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers](https://mlsanity.com/paper/2601.02045/) (2026)
- [AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits](https://mlsanity.com/paper/2610.12545/) (2026)

## Abstract (arXiv)

We propose LangProp, a framework for iteratively optimizing code generated by large language models (LLMs), in both supervised and reinforcement learning settings. While LLMs can generate sensible coding solutions zero-shot, they are often sub-optimal. Especially for code generation tasks, it is likely that the initial code will fail on certain edge cases. LangProp automatically evaluates the code performance on a dataset of input-output pairs, catches any exceptions, and feeds the results back to the LLM in the training loop, so that the LLM can iteratively improve the code it generates. By adopting a metric- and data-driven training paradigm for this code optimization procedure, one could easily adapt findings from traditional machine learning techniques such as imitation learning, DAgger, and reinforcement learning. We show LangProp's applicability to general domains such as Sudoku and CartPole, as well as demonstrate the first proof of concept of automated code optimization for autonomous driving in CARLA. We show that LangProp can generate interpretable and transparent policies that can be verified and improved in a metric- and data-driven way. Our code is available at https://github.com/shuishida/LangProp.