mlsanityData to 7 Oct 2026

Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair

arXiv 2609.14913 ↗First posted 14 Sep 2026cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 21 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

8 of 21 references.

References · 8

  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  2. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  4. 2018code2vec: Learning Distributed Representations of Codecited by 249
  5. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 177
  6. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  7. 2023An Analysis of the Automatic Bug Fixing Performance of ChatGPTcited by 108
  8. 2018Nopol: Automatic Repair of Conditional Statement Bugs in Java Programscited by 32

Built on by

Not cited yet.