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

• URL: http://arxiv.org/abs/2401.10314v2
• Date: Fri, 3 May 2024 16:15:45 GMT
• Title: LangProp: A code optimization framework using Large Language Models applied to driving
• Authors: Shu Ishida, Gianluca Corrado, George Fedoseev, Hudson Yeo, Lloyd Russell, Jamie Shotton, João F. Henriques, Anthony Hu,
• Abstract summary: LangProp is a framework for iteratively optimizing code generated by large language models (LLMs) We show how LangProp can generate interpretable and transparent policies that can be verified and improved in a metric- and data-driven way.
• Score: 17.581983909703283
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• Code Evolution Graphs: Understanding Large Language Model Driven Design of Algorithms [2.827573861233375]
  Large Language Models (LLMs) have demonstrated great promise in generating code. We show results for three benchmark problem classes and demonstrate novel insights.
  arXiv  Detail & Related papers  (2025-03-20T19:30:22Z)
• DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs [56.24431208419858]
  We introduce underlinetextbfDirect Preference Learning with Only underlinetextbfSelf-Generated underlinetextbfTests and underlinetextbfCode (DSTC) DSTC uses only self-generated code snippets and tests to construct reliable preference pairs.
  arXiv  Detail & Related papers  (2024-11-20T02:03:16Z)
• Crystal: Illuminating LLM Abilities on Language and Code [58.5467653736537]
  We propose a pretraining strategy to enhance the integration of natural language and coding capabilities. The resulting model, Crystal, demonstrates remarkable capabilities in both domains.
  arXiv  Detail & Related papers  (2024-11-06T10:28:46Z)
• Effi-Code: Unleashing Code Efficiency in Language Models [17.355845751737423]
  Effi-Code is an approach to enhancing code generation in large language models. Effi-Code offers a scalable and generalizable approach to improving code generation in AI systems.
  arXiv  Detail & Related papers  (2024-10-14T07:05:51Z)
• Steering Large Language Models between Code Execution and Textual Reasoning [22.279107036500083]
  Textual reasoning has inherent limitations in solving tasks with challenges in math, logics, optimization, and searching. The recently released OpenAI GPT Code Interpreter and multi-agent frameworks such as AutoGen have demonstrated remarkable proficiency of integrating code generation and execution. We propose three methods to better steer LLM code/text generation and achieve a notable improvement.
  arXiv  Detail & Related papers  (2024-10-04T15:44:47Z)
• When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention [43.39584272739589]
  We introduce CodeFast, an inference acceleration approach for Code LLMs on code generation. Key idea of CodeFast is to terminate the inference process in time when unnecessary excess tokens are detected. We conduct extensive experiments with CodeFast on five representative Code LLMs across four widely used code generation datasets.
  arXiv  Detail & Related papers  (2024-07-29T14:27:08Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation [22.219645213202178]
  This paper proposes the "Semantic Chain-of-Thought" approach to intruduce semantic information of code, named SeCoT. We show that SeCoT can achieves state-of-the-art performance, greatly improving the potential for large models and code generation.
  arXiv  Detail & Related papers  (2023-10-16T05:09:58Z)
• Evaluating and Explaining Large Language Models for Code Using Syntactic Structures [74.93762031957883]
  This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code. At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes. We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
  arXiv  Detail & Related papers  (2023-08-07T18:50:57Z)
• Coarse-Tuning Models of Code with Reinforcement Learning Feedback [0.0]
  Large Language Models (LLMs) pre-trained on code have emerged as the dominant approach to program synthesis. We propose RLCF, that further trains a pre-trained LLM via reinforcement learning, using feedback from a grounding function that scores the quality of the code.
  arXiv  Detail & Related papers  (2023-05-25T22:09:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.