AdaRepair-Mem：面向仓库级程序修复的自适应经验编排
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
浏览论文内容
中文总结 AI 辅助
针对仓库级程序修复中记忆不平衡、冗余和阶段错配问题，提出自适应经验检索框架，通过覆盖感知、质量选择和阶段路由提升修复性能。
中文摘要 AI 辅助
近期基于记忆增强的仓库级程序修复方法通过复用历史修复经验来提升基于大语言模型的问题解决能力。然而，我们的分析揭示了现有仓库级记忆检索存在的三个局限。首先，情景记忆在仓库间高度不平衡，导致低资源仓库获得的有效支持很少。其次，更多的记忆并不会单调地带来更高的修复成功率，这表明相关性、质量和冗余度比原始记忆量更为重要。第三，记忆积累存在阶段错配：仓库可能包含大量复现经验，但补丁生成或补丁优化经验却很少。为解决这些问题，我们提出了一种面向仓库级程序修复的自适应经验检索框架。该框架引入了覆盖感知检索，当同仓库记忆不足时，回退到跨仓库或基于修复类型的记忆；质量感知选择，根据相关性、历史效用、特异性和冗余度对记忆进行排序；以及阶段感知路由，将复现、定位、补丁生成、补丁优化和验证等阶段的记忆分离并分别检索。在SWE-Bench-Lite和SWE-Bench-Verified上的评估表明，所提出的框架提升了覆盖不足仓库上的修复性能，减少了噪声记忆检索，并更好地支持了从失败到成功的补丁优化。我们的结果表明，记忆增强修复的关键并非简单地积累更多经验，而是在正确的修复上下文中检索正确的经验。
英文摘要
Recent memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution. However, our analysis reveals three limitations in existing repository-level memory retrieval. First, episodic memory is highly imbalanced across repositories, leaving low-resource repositories with little effective support. Second, more memory does not monotonically lead to higher repair success, suggesting that relevance, quality, and redundancy matter more than raw memory volume. Third, memory accumulation is phase-misaligned: repositories may contain many reproduction experiences but few patch or refinement experiences. To address these problems, we propose an adaptive experience retrieval framework for repository-level program repair. Our framework introduces coverage-aware retrieval, which falls back to cross-repository or repair-type-based memories when same-repository memory is insufficient; quality-aware selection, which ranks memories by relevance, historical utility, specificity, and redundancy; and stage-aware routing, which separates and retrieves memories for reproduction, localization, patch generation, patch refinement, and validation. Evaluated on SWE-Bench-Lite and SWE-Bench-Verified, the proposed framework improves repair performance on under-covered repositories, reduces noisy memory retrieval, and better supports failed-to-fixed patch refinement. Our results show that the key to memory-augmented repair is not simply accumulating more experiences, but retrieving the right experiences for the right repair context.
发表机构
- Zhejiang University（浙江大学）
- Tencent（腾讯）
机构由 AI 辅助整理，请以论文原文为准。
