Multi-Agent Coordinated Rename Refactoring
🤖 AI Summary
This work proposes the first multi-agent framework for coordinated renaming refactoring, a task that is typically tedious and error-prone, with existing approaches often yielding false positives or incomplete suggestions. The method infers the scope of related identifiers from an initial developer-provided rename, precisely delineates refactoring boundaries by integrating natural language declarations with program analysis, and automatically executes project-wide coordinated renaming using trusted IDE refactoring APIs. By introducing multi-agent collaboration into code refactoring for the first time, the approach synergistically combines large language models, program analysis, and IDE toolchains to substantially reduce manual effort, effectively eliminate false positives and omissions, and significantly enhance both the accuracy and efficiency of the refactoring process.
Application Category
📝 Abstract
The primary value of AI agents in software development lies in their ability to extend the developer's capacity for reasoning and action, not to supplant human involvement. To showcase how to use agents working in tandem with developers, we designed a novel approach for carrying out coordinated renaming. Coordinated renaming, where a single rename refactoring triggers refactorings in multiple, related identifiers, is a frequent yet challenging task. Developers must manually propagate these rename refactorings across numerous files and contexts, a process that is both tedious and highly error-prone. State-of-the-art heuristic-based approaches produce an overwhelming number of false positives, while vanilla Large Language Models (LLMs) provide incomplete suggestions due to their limited context and inability to interact with refactoring tools. This leaves developers with incomplete refactorings or burdens them with filtering too many false positives. Coordinated renaming is exactly the kind of repetitive task that agents can significantly reduce the developers'burden while keeping them in the driver's seat. We designed, implemented, and evaluated the first multi-agent framework that automates coordinated renaming. It operates on a key insight: a developer's initial refactoring is a clue to infer the scope of related refactorings. Our Scope Inference Agent first transforms this clue into an explicit, natural-language Declared Scope. The Planned Execution Agent then uses this as a strict plan to identify program elements that should undergo refactoring and safely executes the changes by invoking the IDE's own trusted refactoring APIs. Finally, the Replication Agent uses it to guide the project-wide search. We first conducted a formative study on the practice of coordinated renaming in 609K commits in 100 open-source projects and surveyed 205 developers ...
Problem
Research questions and friction points this paper is trying to address.
coordinated renaming
refactoring
multi-agent
software development
false positives
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent system
coordinated renaming
refactoring automation
scope inference
IDE-integrated agents
🔎 Similar Papers
No similar papers found.
