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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vinh, Nguyen Phu, Hoang, Anh Chung, Ngo, Chris, Hy, Truong-Son
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908401924046848
author Vinh, Nguyen Phu
Hoang, Anh Chung
Ngo, Chris
Hy, Truong-Son
author_facet Vinh, Nguyen Phu
Hoang, Anh Chung
Ngo, Chris
Hy, Truong-Son
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles
Vinh, Nguyen Phu
Hoang, Anh Chung
Ngo, Chris
Hy, Truong-Son
Software Engineering
Artificial Intelligence
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.
title Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2506.08173