发表机构
Concordia University（康考迪亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RETRACE通过结合端点视图和开发视图，利用CI执行证据从纠缠的PR历史中重构问题级修复经验，在CI-REPAIR-BENCH上将多个LLM智能体的Pass@1提升至31.9%至32.8%，证明历史CI修复可作为可复用经验。
AI 中文摘要
大型语言模型（LLM）智能体越来越多地复用先前经验，但大多数方法假设问题和解决方案已经对齐。软件历史很少提供这种对齐：一个拉取请求（PR）可能包含多个持续集成（CI）问题、失败的尝试、回退的编辑和不相关的更改，使得哪些更改解决了哪个问题变得模糊不清。我们提出了RETRACE，一个从这类历史中重构问题级修复经验的框架。RETRACE结合了端点视图（从通过修订中保留的更改向后推理）和开发视图（通过提交历史向前追踪修复演化）。CI执行证据调和了这两种视图，恢复的经验以三个抽象级别表示，从具体修复到可迁移的修复模式。对于新的失败，RETRACE检索相关的问题级经验以指导修复。在CI-REPAIR-BENCH上，该基准包含来自12个失败类别的101个仓库的565个PR级修复，RETRACE将mini-SWE-agent的Pass@1从19.6%提升至31.9%（使用MiniMax-M2.5），并从23.3%提升至32.8%（使用DeepSeek-V4-Flash）。在匹配的子集上，Codex从15.5%提升至27.5%。结合两种视图始终优于单独使用任何一种，表明恢复问题-更改对齐能使历史CI修复作为可复用的修复经验。
英文摘要
Large language model (LLM) agents increasingly reuse prior experience, but most approaches assume that problems and solutions are already aligned. Software histories rarely provide this alignment: a pull request (PR) may contain multiple continuous integration (CI) problems, failed attempts, reverted edits, and unrelated changes, obscuring which changes resolve each problem. We present RETRACE, a framework for reconstructing problem-level repair experience from such histories. RETRACE combines an endpoint view that reasons backward from changes retained in the passing revision with a development view that traces repair evolution forward through commit history. CI execution evidence reconciles the two views, and the recovered experience is represented at three abstraction levels, from concrete fixes to transferable repair patterns. For new failures, RETRACE retrieves relevant problem-level experience to guide repair. On CI-REPAIR-BENCH, comprising 565 PR-level repairs from 101 repositories across 12 failure categories, RETRACE improves mini-SWE-agent Pass@1 from 19.6% to 31.9% with MiniMax-M2.5 and from 23.3% to 32.8% with DeepSeek-V4-Flash. On a matched subset, Codex improves from 15.5% to 27.5%. Combining both views consistently outperforms either alone, showing that recovering problem-change alignment enables historical CI repairs to serve as reusable repair experience.
