SOURCE-LINKED INTELLIGENCE

RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Repository-scale refactoring requires coding agents to propagate a single change across many interdependent files without altering program behavior, yet to our knowledge no existing harness isolates the design choices that determine agent success on this task. We present RefactorPlatform, an open-source evaluation harness that holds the environment fixed and varies each design axis explicitly: model backbone (via OpenRouter and GitHub Copilot CLI), execution regime (baseline, retrieval-augmented, and multi-agent), and prompt specificity. Each run executes in an isolated workspace with live ter

Read original source ↗ Open in workspace

recordType

paper

region

Global