From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
For automated program repair, ConRAD provides a scalable inference-time alternative to forward exploration by reusing successful repair patterns from the same repository.
ConRAD improves repository-level program repair by distilling repair plans from prior resolved issues, achieving 10.4% (GPT-4o), 8.6% (DeepSeek-V3), and 10.3% (GPT-5) Pass@1 gains on SWE-Bench Lite without fine-tuning or search.
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.