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

arXiv:2401.10314v2 Announce Type: replace-cross
Abstract: 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 …

arxiv code cs.ai cs.lg cs.ro cs.se driving framework language language models large language large language models optimization type