Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles

TL;DR

Repeton is an open-source framework that uses structured, iterative patch-and-test cycles guided by LLMs to improve code debugging and repair in real-world software repositories, emphasizing interpretability and validation.

Contribution

Repeton introduces a modular, stepwise approach to automated bug fixing that avoids embedding retrieval, enhancing transparency and effectiveness in software debugging tasks.

Findings

Performs well on the SWE-bench Lite benchmark

Outperforms RAG-based methods in patch validity

Provides interpretable, verifiable code fixes

Abstract

Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability. We present Repeton, a fully open-source framework that leverages LLMs for precise and automated code manipulation in real-world Git repositories. Rather than generating holistic fixes, Repeton operates through a structured patch-and-test pipeline: it iteratively diagnoses issues, proposes code changes, and validates each patch through automated testing. This stepwise process is guided by lightweight heuristics and development tools, avoiding reliance on embedding-based retrieval systems. Evaluated on the SWE-bench Lite benchmark, our method shows good performance compared to RAG-based methods in both patch validity and interpretability. By decomposing software engineering tasks into modular, verifiable stages, Repeton provides a practical path toward scalable and transparent autonomous debugging.