将需求到修复的工件外部化为可观察轨迹，用于基于LLM的程序修复
Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair
浏览论文内容
中文总结 AI 辅助
本文提出THEMIS，一种通过外部化需求到修复过程的可观察工件来支持仓库级程序修复的工作流，实验表明其能有效提升修复效果并支持跨阶段审计。
中文摘要 AI 辅助
仓库级修复不仅需要正确的补丁，还需要可检查的记录，以解释问题需求如何转化为代码更改及编辑后的证据。我们贡献了THEMIS，一种阶段感知的修复工作流，通过语义解释、运行时需求-代码图、图派生的开发者指导、保留的修复理由与补丁以及编辑后审计记录，将这一需求到修复的过程外部化。对300个SWE-bench Lite案例的回顾性审计表明，这些工件为跨阶段检查提供了广泛支持：288个案例可获得完整的开发者理由，214个案例（71.3%）保留了连接所选阶段的完整审计字段集。保留的记录进一步实现了跨阶段对应关系的系统测量：目标符号在62.6%的开发者理由和62.8%的补丁中重复出现，当包含相关符号时，这一比例升至75.8%。在一项配对的100案例比较中，关系型工作流解决了19个案例，而直接相同输入条件解决了9个；由于两种条件在分析器输出、图派生蒸馏和法官记录方面也存在差异，我们将其报告为初步的工作流级证据，而非图组件的因果效应。综合来看，这些结果表明THEMIS使原本隐式的需求到修复转换变得可检查，从而能够系统地考察修复决策如何在各阶段持续、对齐和演变。
英文摘要
Repository-level repair requires not only correct patches but also inspectable records that explain how issue requirements are translated into code changes and post-edit evidence. We contribute THEMIS, a stage-aware repair workflow that externalizes this requirement-to-repair process through semantic interpretation, a runtime requirement-code graph, graph-derived Developer guidance, retained repair rationale and patches, and post-edit audit records. A retrospective audit of 300 SWE-bench Lite cases demonstrates that these artifacts provide broad support for cross-stage inspection: a complete Developer rationale is available for 288 cases, and 214 cases (71.3%) retain a complete audited field set connecting the selected stages. The retained records further enable systematic measurement of cross-stage correspondence: target symbols recur in 62.6% of Developer rationales and in 62.8% of patches, rising to 75.8% when related symbols are included. In a paired 100-case comparison, the relational workflow resolves 19 cases versus 9 for the direct same-input condition; because the two conditions also differ in Analyzer output, graph-derived distillation, and Judge records, we report this as preliminary, workflow-level evidence rather than a causal effect of the graph component. Together, these results show that THEMIS makes otherwise implicit requirement-to-repair transitions inspectable, enabling systematic examination of how repair decisions persist, align, and evolve across stages.
发表机构
- Rikkyo University（立教大学）
机构由 AI 辅助整理，请以论文原文为准。
