arXiv cs.AI· Elad Sharony, Ido Greenberg, Jialin Song, Shie Mannor, Gal Chechik, Eli Meirom·· 3 天前AI 评分29
CodeTriage：让 LLM 代码修复的每次搜索都更高效
Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair
AI 导读
研究者提出 CodeTriage，一个 0.6B 参数的学习型策略，在生成和测试修订代码前，先读取测试输出、失败诊断和候选编辑，预测该编辑达到修复所需的修复步数分布，从而对多个程序的待处理编辑统一排序。
正文 · 原文
Abstract:Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions. Each revision is costly, making the choice of which repair to pursue important for efficiency. Existing search policies rely on test pass rates and search statistics, ignoring the details of test failures and proposed edits. We introduce CodeTriage, a learned policy that prioritizes edits before their revised programs are generated and tested. Its 0.6B-parameter model reads the test output, failure diagnosis, and proposed edit, then predicts a distribution over the number of repair steps needed to reach a fix through that edit. These predictions prioritize all pending edits across programs before generating and testing the revised code. On held-out repair tasks, CodeTriage finds fixes with 21% fewer program revisions and 12% fewer output tokens than the strongest baseline on each metric. Without retraining, it achieves the highest average success across search budgets for each of 11 unseen repair LLMs. Ablations show that both the failure context and edit text, as well as comparisons across programs, improve search. We also release a corpus of 12.2 million program versions from four LLMs, organized into repair trees with proposed edits and test results.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.15894 [cs.LG] |
| (or arXiv:2610.15894v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15894 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elad Sharony [view email]
[v1]
Sun, 11 Oct 2026 20:19:05 UTC (524 KB)
来源：arXiv cs.AI · arxiv.org