AI Paper Atlas

Research map / Large language models / Agents, code and math

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

Chenglin Li, Yisen Xu, Zehao Wang, Shin Hwei Tan, Tse-Hsun Chen

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the Exemplar Guardian filter (ablation)ConRAD · SWE-Bench LitePass@1 (%): 33.7 -> 37.7 (GPT-4o); 37.7 -> 40.0 (GPT-5); 30.0 -> 35.6 (DeepSeek-V3)Improved
use backward reasoning distillation instead of MCTS forward exploration (ablation)ConRAD · SWE-Bench Lite (100 samples)Pass@1 (%): 28.0 -> 41.0Improved
MCTS forward search uses more compute than BRD (ablation)ConRAD · SWE-Bench Lite (100 samples)LLM calls and tokens: 9.71x more LLM calls, 2.47x more tokensHurt
add distilled reasoning plan on top of exemplar and patch injection (ablation)ConRAD · SWE-Bench Lite (100 samples)Pass@1 (%): 32.0 -> 41.0Improved
inject raw exemplar issue and ground-truth patch without a plan (ablation)Agentless · SWE-Bench Lite (100 samples)Pass@1 (%): 34.0 -> 32.0Hurt
use top-1 exemplar rather than top-3 exemplar (ablation)ConRAD · SWE-Bench Lite (100 samples)Pass@1 (%): 39.0 -> 45.0Improved
add ConRAD to AgentlessAgentless · SWE-Bench LitePass@1 (%): 27.3 -> 37.7 (GPT-4o)Improved
add ConRAD to Agentless with GPT-5Agentless · SWE-Bench LitePass@1 (%): 29.7 -> 40.0Improved
add ConRAD to Agentless with DeepSeek-V3Agentless · SWE-Bench LitePass@1 (%): 27.0 -> 35.6Improved
add ConRAD to mini-SWE-agentmini-SWE-agent · SWE-Bench Lite (100 samples)Pass@1 (%): 48.0% -> 58.0%Improved
add ConRAD to Agentless with GPT-5Agentless · SWE-Bench Litefile localization accuracy (%): 85.0% -> 86.3%No clear effect
add ConRAD to Agentless with GPT-4oAgentless · SWE-Bench Litefunction localization accuracy (%): 51.0% -> 59.3%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy