# RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair

arXiv: https://arxiv.org/abs/2610.04658 · HTML: https://mlsanity.com/paper/2610.04658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation](https://mlsanity.com/paper/2503.06680/) (2025)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair](https://mlsanity.com/paper/2506.10484/) (2025)
- [ThinkRepair: Self-Directed Automated Program Repair](https://mlsanity.com/paper/2407.20898/) (2024)
- [SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration](https://mlsanity.com/paper/2603.03823/) (2026)
- [Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling](https://mlsanity.com/paper/2510.11838/) (2025)
- [Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey](https://mlsanity.com/paper/2601.11655/) (2026)
- [LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation](https://mlsanity.com/paper/2506.03691/) (2025)
- [From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair](https://mlsanity.com/paper/2601.23257/) (2026)
- [CI-Repair-Bench: A Repository-Aware Benchmark for Automated Patch Validation via CI Workflows](https://mlsanity.com/paper/2604.27148/) (2026)
- [Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models](https://mlsanity.com/paper/2601.22264/) (2026)
- [Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents](https://mlsanity.com/paper/2607.29658/) (2026)

## Abstract (arXiv)

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.