Automated Program Repair

Follow this topic Ask about this topic

Automated program repair studies how to find and correct bugs while preserving a program’s intended behavior. Approaches range from search-based patch generation and program analysis to language models that use fault localization, repository context, retrieved examples, and iterative agent workflows. Tests, runtime traces, static analysis, and formal methods can guide or verify repairs, with benchmarks spanning small functions, repositories such as those tested by SWE-bench, and security or hardware code. A central challenge is that compiling or passing available tests does not guarantee a secure, semantically correct, minimal fix, so stronger oracles must be balanced against context limits, cost, and generalization.

Latest papers

158 papers32 papers in the last four weeks, up 68% on the four weeks before. 0.2% of all new papers.

JevVibe: Efficient Classification-Guided Secure Code Generation
Sep 28, 2026Arshak Rezvani, Sasha Behrouzi, Ahmad-Reza SadeghiAutomated Program Repair Software Vulnerability Detection
Technical University of Darmstadt, Germany
Improving Large Language Models for Code through Runtime Program-State Reasoning
Sep 28, 2026Hongwei Li, Spandan Garg, Yufan HuangAutomated Program Repair Automated Test Generation
University of California, Santa Barbara · Microsoft
Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?
Sep 24, 2026Alexandru Stefan Stoica, Traian Rebedea, Marian Cristian MihaescuLLM Evaluation Automated Program Repair
University Politehnica of Bucharest Bucharest, Romania · University of Craiova Craiova, Romania
Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution
Sep 22, 2026Veronica Poweska, Ariana Oyanguren, Jessica Pourleyli +2Software Engineering Automated Program Repair
Toronto Metropolitan University, Computer Science, Toronto, Ontario, Canada · Toronto Metropolitan University, Creative School, Toronto, Ontario, Canada · Flybits, Creative AI Hub, Toronto, Ontario, Canada
Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
Sep 22, 2026Om Nepal, Sushant Aryal, Oluseyi Olukola +1Automated Program Repair LLMs for Cybersecurity
School of Computing Sciences and Computer Engineering, The University of Southern Mississippi, Hattiesburg, MS 39406, 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
RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views
Sep 15, 2026Yunxiang Zhang, Haiquan Wang, JiaWei Guo +5Software Engineering Agents Automated Program Repair
Beihang University · Independent Researcher
Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair
Sep 14, 2026Zewen Tao, Shin-nosuke IshikawaAutomated Program Repair Reasoning Trace Analysis
Rikkyo University
RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization
Sep 10, 2026Binghao Ji, Di Huang, Jiahui Fang +1Automated Program Repair Automated Heuristic Design
Jiangsu Key Laboratory of Urban ITS, Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, School of Transportation, Southeast University, Nanjing, China, 211189.
If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs
Sep 9, 2026Xietao Wang-Lin, Anton Isopoussu, Louis MahonLLM Self-Correction Automated Program Repair
University of Warwick · UnlikelyAI
ExecCritic: Learn to Test, Test to Improve for Coding Agents
Sep 8, 2026Leitian Tao, Baolin Peng, Haorui Wang +7RL for Code Generation Software Engineering Agents
University of Wisconsin–Madison · Microsoft Research · Georgia Tech
Recompilation Is Not Enough: Test-Guided Decompiled-C Repair
Sep 7, 2026Yuhan Huang, Puzhuo Liu, Jianlei ChiAutomated Program Repair Software Reverse Engineering
Xidian University Xi’an, China · Ant Group Hangzhou, China
The History Is the Detector: Executing CVE Patch History, End-to-End
Sep 4, 2026Qiushi Wu, Kevin Eykholt, Youngja Park +4Software Vulnerability Detection Automated Program Repair
IBM Research
H2LooP Telecom Model v1: From Telecom Comprehension to Autonomous Issue and PR Resolution
Sep 4, 2026Amit Singh, Vedant Nipane, Mayank Goel +2Code Generation LLM Fine-Tuning
Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
Sep 4, 2026Xuemeng Cai, Jiakun Liu, Linhan Yang +2Automated Program Repair Hallucination in Language Models
School of Computing and Information Systems, Singapore Management University, Singapore · Harbin Institute of Technology, Harbin, China
SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents
Sep 3, 2026Xin He, Yanlin Wang, Mingwei Liu +3Software Engineering Agents Automated Program Repair
School of Software Engineering, Sun Yat-sen University · College of Computer Science and Technology, Zhejiang University · School of Big Data and Software Engineering, Chongqing University +1
PatchBench: Evaluating AI Agents for Vulnerability Patching
Sep 3, 2026Chihao Shen, Jiacheng Li, Aastha Mahajan +3Automated Program Repair Neural Network Memorization
University of Maryland
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Sep 3, 2026Tongyao Zhu, Wei Hern Lim, Min-Yen KanAutomated Program Repair Language Model Editing
National University of Singapore
Dictionary-Guided Mutation Operators for Automated HDL Repair
Sep 1, 2026Maisha Mastora, Dean SullivanAutomated Program Repair Electronic Design Automation
Department of Electrical and Computer Engineering University of New Hampshire Durham, NH, USA
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
Sep 1, 2026Anik JhaAutomated Program Repair Fault Localization
Independent Researcher
DiffPDE: Masked Diffusion Language Models as PDE Solver
Aug 31, 2026Wenxuan Guo, Yuyang Hong, Lubin Fan +4RL for Code Generation Masked Diffusion Models
School of Artificial Intelligence, University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Independent Researcher
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
Aug 25, 2026Yuchuan Wu, Ke Niu, Haiyang Yu +3Parametric CAD Modeling Execution-Guided Code Generation
Fudan University Shanghai, China
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Aug 20, 2026Zhipeng Xu, Jiahao Lu, Yining Zheng +2Software Engineering Automated Program Repair
Shanghai Innovation Institute · Fudan University
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Aug 19, 2026Silin Chen, Han Li, Xiaodong Gu +2Automated Software Engineering LLM Agent Skill Learning
Shanghai Jiao Tong University
LLM-Only PDDL Domain Repair with Open-Weight Models
Aug 18, 2026Nader Karimi Bavandpour, Pascal BercherAutomated Program Repair Symbolic Planning
School of Computing, The Australian National University, Canberra, Australia
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
Aug 17, 2026Mikhail SurikovSecure Code Generation Software Vulnerability Detection
Georgia Institute of Technology Atlanta, Georgia, USA
RAGas: Retrieval-Augmented Gas Optimization for Smart Contracts with Continuous Knowledge Integration
Aug 16, 2026Yishun Wang, Wenjin Yi, Wenkai Li +2Automated Program Repair Static Code Analysis
School of Cyberspace Security, Hainan University
Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair
Aug 16, 2026Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata +24Software Engineering Agents Automated Program Repair
Fujitsu Research of America Santa Clara, CA, USA · Fujitsu Research Kawasaki, Japan · Fujitsu Research of Europe Slough, UK +1
Evaluating Agentic Code Repair Capabilities in Distributed Systems
Aug 14, 2026Yibo Yan, Huijuan Wang, Junzhou He +4AI Coding Agents LLM Agent Evaluation
University of Southern California
The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context
Aug 14, 2026Alexander Adkins, Teimuraz TrapaidzeRetrieval-Augmented Generation IR Evaluation
Make Games Initiative

Sep 28, 2026J/K move · Enter open · S save

JevVibe: Efficient Classification-Guided Secure Code Generation

Arshak Rezvani, Sasha Behrouzi, Ahmad-Reza Sadeghi

Technical University of Darmstadt, Germany

Automated Program Repair Software Vulnerability Detection Cybersecurity Secure Code Generation

Open paper AskPDF arXiv

Large language models can generate functionally correct code that still contains security weaknesses, motivating repair pipelines that first diagnose a weakness type before deciding how to fix it. The Common Weakness Enumeration (CWE) provides a standardized vocabulary for such diagnoses, but asking an autoregressive language model to generate a CWE label and extracting it from the response raises questions about output validity, speed, and cost, as well as accuracy. We evaluate Jev, a decision model that instead selects directly from a declared set of candidates and returns a probability for each, against six open-weight autoregressive models and a frontier proprietary model, GPT-5.6-Sol, on a controlled 50-way CWE classification task over 1,916 CyberSecEval benchmark examples. Jev outperforms all six open-weight baselines on every classification and ranking metric, while its comparison with GPT-5.6-Sol depends on the metric: GPT-5.6-Sol achieves higher Top-1 accuracy and Macro-F1, whereas Jev achieves higher Top-3 and Top-5 accuracy and a nearly identical MRR, at

6.27\times

lower median API latency and

55.9\times

lower estimated API cost. We further build JevVibe, a diagnosis-guided repair agent that uses predicted CWE labels to repair code generated by Qwen2.5-Coder-32B-Instruct. With Jev providing the diagnosis, the agent increases the detector-measured security pass rate from 63.5% before repair to 70.7%, compared with 66.1% for LLM-guided repair. These results show that JevVibe is effective at improving the security of generated code, with Jev providing reliable and efficient CWE classification.