[论文解读] Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents

Xiang Li, Zhiwei Fei+4 more|arXiv (Cornell University)|Feb 10, 2026

Software Engineering Research被引用 0

一句话总结

论文引入一个环境驱动的多智能体框架，将自动化环境设置与代码迁移紧密结合，利用基于大语言模型的智能体实现端到端、具环境感知的迁移。

ABSTRACT

Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on automated code migration which including refactoring, API adaptation, and dependency updates has advanced rapidly, the exploration of the automated environment interaction that must accompany it remains relatively scarce. In practice, code and its environment are intricately intertwined. Relying solely on static analysis of the environment leads to an inadequate understanding of the target setting, prolongs feedback cycles, and consequently causes significant rework and project delays, thereby reducing overall efficiency. We contend that successful software evolution demands a holistic perspective that integrates both code and environment migration. To understand the current landscape and challenges, we first provide an overview of the status of automated environment construction. We then propose a novel framework paradigm that tightly integrates automated environment setup with the code migration workflow. Finally, we explore the challenges and future directions for automated environment interaction within the code migration domain. Our findings emphasize that without automated environment interaction, the automation of code migration is only half complete.

研究动机与目标

• 突出静态环境分析在代码迁移中的局限性以及对环境感知迁移的需求。
• 提出一个将环境构建、代码迁移与测试整合到闭环工作流程的框架。
• 证明基于LLM的智能体如何协作构建环境、修改代码并验证迁移。

提出的方法

• 定义一个代理系统，包含迁移代理（M-Agent）、环境代理（E-Agent）和测试套件代理（T-Agent）。
• 描述每个代理如何使用特定工具集来执行迁移、环境搭建和测试任务。
• 描述一个四阶段迁移循环：计划、自动环境搭建、测试验证和反馈改进。
• 解释E-Agent如何作为核心验证枢纽，构建环境、运行测试并报告诊断信息。
• 概述三代理协作如何实现从迁移分析到环境构建与验证的端到端自动化。

Figure 1. An implicit and subtle runtime error caused by the library upgrade, which is hard to catch by static analysis.

实验结果

研究问题

• RQ1 自动化环境交互如何在静态分析的对比中提升代码迁移的可靠性和效率？
• RQ2 一个环境驱动的多智能体工作流是否能够提供从环境搭建、执行到测试的端到端自动化？
• RQ3 在一个连贯的迁移循环中，M-Agent、E-Agent和T-Agent扮演哪些角色，它们如何通信以闭环？

主要发现

• 提出一个以环境驱动的框架，将环境搭建转化为自动迁移的核心驱动。
• 环境代理构建可重复、可执行的环境，并提供诊断报告以指导修复。
• 迁移代理生成迁移后的代码和依赖更新，接受环境代理的反馈进行修正。
• 测试套件代理在经过验证的环境中创建并运行测试，以确保迁移后功能等价。
• 闭环工作流程旨在提升迁移的可靠性，并提高对CI/CD中环境漂移的鲁棒性。

Figure 2. Examples of error types that can only be discovered through dynamic environment interaction.