Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Lan- guage Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on automated code migration—encompassing refactoring, API adaptation, and dependency updates—has advanced rapidly, the exploration of the automated environment interaction that must accompany it re- mains relatively scarce. In practice, code and its environment are intricately intertwined. Relying solely on static analysis of the envi- ronment leads to an inadequate understanding of the target setting, prolongs feedback cycles, and consequently causes significant re- work and project delays, thereby reducing overall efficiency. We contend that successful software evolution demands a holistic per- spective 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 construc- tion. 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 environ- ment interaction, the automation of code migration is only half complete.
Tue 14 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change
11:00 - 12:30 | |||
11:00 60mKeynote | An Agentic Approach to Optimize Agentic Workflows ReCode 2026 Alvin Cheung University of California at Berkeley | ||
12:00 15mTalk | Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents ReCode 2026 Xiang Li University College London, Zhiwei Fei Nanjing University, Ying Ma Brunel University, Jerry Zhang Delysium, Federica Sarro University College London, He Ye University College London (UCL) | ||
12:15 15mTalk | CNnotator: LLM-Guided Memory Safety Annotation Synthesis ReCode 2026 | ||