$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911024314056704 |
|---|---|
| author | Liu, Quanming Bu, Xupeng Yan, Zhichao Li, Ru |
| author_facet | Liu, Quanming Bu, Xupeng Yan, Zhichao Li, Ru |
| contents | Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models (LLMs) and the Chain-of-Thought (CoT) techniques have significantly enhanced the reasoning capabilities of these models. However, due to the complex logic and multi-step reasoning ability needed, the application of CoT techniques in the APR domain remains insufficient. This study systematically evaluates the performance of several common CoT techniques in APR tasks and proposes an innovative framework $T^3$, which integrates the powerful reasoning capabilities of LLMs with tree search, effectively improving the precision of generating candidate repair solutions. Furthermore, $T^3$ provides valuable guidance for optimizing sample selection and repair strategies in APR tasks, establishing a robust framework for achieving efficient automated debugging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21211 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | $T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models Liu, Quanming Bu, Xupeng Yan, Zhichao Li, Ru Software Engineering Artificial Intelligence Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models (LLMs) and the Chain-of-Thought (CoT) techniques have significantly enhanced the reasoning capabilities of these models. However, due to the complex logic and multi-step reasoning ability needed, the application of CoT techniques in the APR domain remains insufficient. This study systematically evaluates the performance of several common CoT techniques in APR tasks and proposes an innovative framework $T^3$, which integrates the powerful reasoning capabilities of LLMs with tree search, effectively improving the precision of generating candidate repair solutions. Furthermore, $T^3$ provides valuable guidance for optimizing sample selection and repair strategies in APR tasks, establishing a robust framework for achieving efficient automated debugging. |
| title | $T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2506.21211 |