PatchRecall: Patch-Driven Retrieval for Automated Program Repair

Mahir Labib Dihan; Faria Binta Awal; Md. Ishrak Ahsan

cs.SEApr 12, 2026

PatchRecall: Patch-Driven Retrieval for Automated Program Repair

Authors: Mahir Labib Dihan, Faria Binta Awal, Md. Ishrak Ahsan

Organizations: Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET)

Abstract

Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files introduces noise and degrades efficiency. To address this tradeoff, we propose PatchRecall, a hybrid retrieval approach that balances recall with conciseness. Our method combines two complementary strategies: (1) codebase retrieval, where the current issue description is matched against the codebase to surface potentially relevant files, and (2) history-based retrieval, where similar past issues are leveraged to identify edited files as candidate targets. Candidate files from both strategies are merged and reranked to produce the final retrieval set. Experiments on SWE-Bench demonstrate that PatchRecall achieves higher recall without significantly increasing retrieved file count, enabling more effective APR.

Figures & tables

Method	Model	% Resolved
TRAE	Claude 4 Sonnet	75.20
Refact.ai Agent	Claude 4 Sonnet	74.40
Moatless Tools	Claude 4 Sonnet	70.80
OpenHands	Claude 4 Sonnet	70.40
SWE-agent	Claude 4 Sonnet	66.60
SWE-Fixer	Qwen-2.5-7b	32.80

Table 1: Performance comparison on SWE-bench Verified leaderboard.

Figure 1: (a) Overview of failure patterns across repositories, difficulty levels, time periods, and failure counts. Top-left shows the top 10 repositories with the most all-failed instances. Top-right displays the percentage of each difficulty level that failed across all agents. Bottom-left presents the temporal distribution of all-failed instances from 2018 to 2023. Bottom-right shows the distribution of failure counts, with the red bar highlighting 58 instances where all 18 agents failed. (b) Error frequencies by repository across different error types. The chart reveals repository-specific error patterns, with TypeError dominating in sphinx-doc, AssertionError prevalent across multiple repositories, and varying frequencies of AttributeError, KeyError, and ValueError across different codebases. (c) Distribution of instance failure counts across agents. The histogram shows the number of instances for each failure count (1-18 agents). The red-highlighted bar at failure count 18 represents 58 instances where all agents failed, indicating particularly challenging cases in the benchmark.

Figure 2: Frequency distribution plot showing how many files were modified in the patches included in the SWE-bench-verified dataset. Our empirical analysis reveals that in more than 80% of cases, only a single file actually requires modification. And in all of the patches, less than 10 files were modified.

Figure 3: Overview of our proposed hybrid retrieval workflow. (A) History-Based Retrieval: The current issue is compared with the SWE-bench-unverified dataset using sentence transformer to retrieve the top-10 most similar issues. From their associated patches, the modified files are extracted, and scored. (B) Direct Codebase Retrieval: In parallel, the current issue is matched against the entire target repository using BM25, producing a ranked list of candidate files by textual relevance. (C) Hybrid Score Fusion & Re-ranking: Scores from both retrieval streams are min–max normalized and combined via the hybrid scoring function $H(f)$ . The fused list is re-ranked to produce the top- $k$ files, which are supplied as input context to the LLM for patch generation.

Figure 4: Comparison of recall scores for BM25, TF–IDF, and Sentence Transformer retrievers on SWE-bench-verified. The

x

-axis denotes the number of retrieved files (

k

), while the

y

-axis shows recall. The sentence transformer demonstrates the highest recall across all retrieval depths, highlighting its advantage in bridging semantic gaps between issue descriptions and code.

Figure 5: Recall scores of the proposed hybrid retrieval strategy on SWE-bench-verified for different values of

\alpha

. When

\alpha=0

, the system reduces to pure BM25 retrieval; when

\alpha=1

, it relies solely on issue–patch similarity. Hybrid configurations with

\alpha

between

0.4

and

0.6

achieve the highest recall, demonstrating the benefit of balancing patch-derived evidence with direct textual similarity.

Figure 6: Recall@K comparison between our retrieval methods and the BM25 baseline used in MAGIS. The

x

-axis denotes the number of retrieved files (

k

), while the

y

-axis shows recall percentage. Our sentence transformer retriever, combined with hybrid scoring (

\alpha=0.4

), achieves consistently higher recall, highlighting the effectiveness of semantic and patch-augmented retrieval compared to sparse BM25 retrieval alone.

Automated Program Repair

Automated program repair develops methods that locate software faults and produce validated fixes with limited human effort.

See all 158 papers

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
Mar 1, 2026Zhongqiang Pan, Chuanyi Li, Wenkang Zhong +3Repository-Level Program Repair Automated Program Repair
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Human Language Technology Research Institute, University of Texas at Dallas, Richardson, Texas, USA
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
Sep 17, 2026Z. C. Luo, J. C. Guo, W. J. He +10Automated Program Repair Adaptive Retrieval
Zhejiang University · Tencent
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
Apr 7, 2026Changxin Ke, Rui Zhang, Jiaming Guo +10Automated Program Repair LLM Code Generation
State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Institute of Microelectronics, CAS

Mar 1, 2026J/K move · Enter open · S save

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair

Zhongqiang Pan, Chuanyi Li, Wenkang Zhong, Yi Feng+2

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Human Language Technology Research Institute, University of Texas at Dallas, Richardson, Texas, USA

Repository-Level Program Repair Automated Program Repair Fault Localization

Open paper AskPDF arXiv

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow retrieval or costly agent iterations, falter on complex cross-file issues. To this end, we propose RepoRepair, a novel documentation-enhanced approach for repository-level fault localization and program repair. Our core insight is to leverage LLMs to generate hierarchical code documentation (from functions to files) for code repositories, creating structured semantic abstractions that enable LLMs to comprehend repository-level context and dependencies. Specifically, RepoRepair first employs a text-based LLM (e.g., DeepSeek-V3) to generate file/function-level code documentation for repositories, which serves as auxiliary knowledge to guide fault localization. Subsequently, based on the fault localization results and the issue description, a powerful LLM (e.g., Claude-4) attempts to repair the identified suspicious code snippets. Evaluated on SWE-bench Lite, RepoRepair achieves a 45.7% repair rate at a low cost of

0.44 per fix. On SWE-bench Multimodal, it delivers state-of-the-art performance with a 37.1% repair rate despite a higher cost of

0.56 per fix, demonstrating robust and cost-effective performance across diverse problem domains.

Abstract

Automated Program Repair

Explore similar work

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair

AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization