CROCODIL: Cross-Model Code Editing with LLMs

2026-09-03

AI Summary

研究解决了多模型编辑代码时产生过多修改的问题，通过CROCODIL框架结合相似性和执行奖励减少过度编辑同时保持功能正确性。

Abstract

Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may prefer different models, and individual developers may switch between models across different coding sessions. Because of this, the edits any one model makes are frequently applied to foreign code originally generated by another model. These LLMs are often trained on different datasets, and as a result have different stylistic preferences. Do LLMs behave differently when they edit foreign code originally written by a different LLM with a different coding style? We find that models tend to make more, and often excessive, edits on foreign code. We introduce CROCODIL (Cross-model Code Editing with LLMs), a post-training framework for reducing excessive edits while preserving functional correctness. CROCODIL's similarity reward penalizes large changes, while its execution reward scores build and test success. We use the product of these two rewards to encourage the policy to decrease the edit size without decreasing the edit task success rate. CROCODIL is available at https://github.com/EngineeringSoftware/Crocodil.

Problem

• Large Language Models
• Code Editing
• Cross-Model Edits
• Coding Style

Innovation

• Cross-model Code Editing
• Similarity Reward
• Execution Reward
• Large Language Models