# From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair

arXiv: https://arxiv.org/abs/2601.23257 · HTML: https://mlsanity.com/paper/2601.23257/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 27 of 27)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [In-context Example Selection with Influences](https://mlsanity.com/paper/2302.11042/) (2023)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [MASAI: Modular Architecture for Software-engineering AI Agents](https://mlsanity.com/paper/2406.11638/) (2024)
- [EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair](https://mlsanity.com/paper/2506.10484/) (2025)
- [Reverse-Engineered Reasoning for Open-Ended Generation](https://mlsanity.com/paper/2509.06160/) (2025)
- [SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories](https://mlsanity.com/paper/2509.08724/) (2025)
- [SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning](https://mlsanity.com/paper/2502.20127/) (2025)
- [Enhancing repository-level software repair via repository-aware knowledge graphs](https://mlsanity.com/paper/2503.21710/) (2025)
- [Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute](https://mlsanity.com/paper/2503.23803/) (2025)
- [Meta Prompting for AI Systems](https://mlsanity.com/paper/2311.11482/) (2023)
- [Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling](https://mlsanity.com/paper/2510.11838/) (2025)
- [Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search](https://mlsanity.com/paper/2506.23100/) (2025)
- [PSearch: Search-based Patch Generation in the Era of LLM-based Automated Program Repair](https://mlsanity.com/paper/2507.01827/) (2025)
- [MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution](https://mlsanity.com/paper/2506.12728/) (2025)
- [RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code](https://mlsanity.com/paper/2509.16701/) (2025)

## Built on by (most cited first, 3 of 3)

- [Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework](https://mlsanity.com/paper/2608.08950/) (2026)
- [AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair](https://mlsanity.com/paper/2609.20130/) (2026)
- [RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair](https://mlsanity.com/paper/2610.04658/) (2026)

## Abstract (arXiv)

Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories contain many related issues with shared structure or constraints. Existing methods typically rely on forward exploration, which operates under outcome uncertainty, incurs substantial inference-time overhead, and can drift from the final correct patch. We propose Conditional Reasoning Distillation (ConRAD), which leverages in-repository resolved issues by reconstructing repair reasoning backward from verified patches and distilling outcome-consistent, stage-wise repair reasoning plans. Injected at inference time, these plans guide fault localization and patch generation, replacing open-ended exploration with constrained inference without fine-tuning or search. On SWE-Bench Lite, ConRAD improves Pass@1 by 10.4% (GPT-4o), 8.6% (DeepSeek-V3), and 10.3% (GPT-5), demonstrating a scalable inference-time alternative to forward exploration for long-horizon APR.