mlsanityData to 7 Oct 2026

AutoCodeRover: Autonomous Program Improvement

arXiv 2404.05427 ↗First posted 8 Apr 2024cs.SE cs.AIcited by 272

Not on the map. Why?

Cited by 182 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding. Nevertheless, software engineering involves the process of program improvement apart from coding, specifically to enable software maintenance (e.g. bug fixing) and software evolution (e.g. feature additions). In this paper, we propose an automated approach for solving GitHub issues to autonomously achieve program improvement. In our approach called AutoCodeRover, LLMs are combined with sophisticated code search capabilities, ultimately leading to a program modification or patch. In contrast to recent LLM agent approaches from AI researchers and practitioners, our outlook is more software engineering oriented. We work on a program representation (abstract syntax tree) as opposed to viewing a software project as a mere collection of files. Our code search exploits the program structure in the form of classes/methods to enhance LLM's understanding of the issue's root cause, and effectively retrieve a context via iterative search. The use of spectrum-based fault localization using tests, further sharpens the context, as long as a test-suite is available. Experiments on SWE-bench-lite (300 real-life GitHub issues) show increased efficacy in solving GitHub issues (19% on SWE-bench-lite), which is higher than the efficacy of the recently reported SWE-agent. In addition, AutoCodeRover achieved this efficacy with significantly lower cost (on average, 0.43 USD), compared to other baselines. We posit that our workflow enables autonomous software engineering, where, in future, auto-generated code from LLMs can be autonomously improved.

Key facts. Cited by 272 papers in the map (data through 7 Oct 2026). Builds on 12 of its 52 references that are in the map. First posted on arXiv 8 Apr 2024.

Builds on

12 of 52 references.

References · 12

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  3. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  4. 2023InferFix: End-to-End Program Repair with LLMscited by 113
  5. 2023Impact of Code Language Models on Automated Program Repaircited by 85
  6. 2021A Syntax-Guided Edit Decoder for Neural Program Repaircited by 57
  7. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  8. 2019Getafix: Learning to Fix Bugs Automaticallycited by 40
  9. 2021Trust Enhancement Issues in Program Repaircited by 22
  10. 2021PyCG: Practical Call Graph Generation in Pythoncited by 16
  11. 2019iFixR: Bug Report driven Program Repaircited by 11
  12. 2024PyTy: Repairing Static Type Errors in Pythoncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 33; 2025: 96; 2026: 143.

272 papers.

Sort:

By area:

  1. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 300
  2. 2025SWE-smith: Scaling Data for Software Engineering Agentscited by 255
  3. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  4. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  5. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
  6. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  7. 2025Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingcited by 165
  8. 2024RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learningcited by 146
  9. 2025Evaluation and Benchmarking of LLM Agents: A Surveycited by 145
  10. 2025R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agentscited by 140
  11. 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agentscited by 129
  12. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
38 more
  1. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  2. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 111
  3. 2025Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scalingcited by 93
  4. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
  5. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  6. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  7. 2024SpecRover: Code Intent Extraction via LLMscited by 71
  8. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agentscited by 66
  9. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  10. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  11. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  12. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  13. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  14. 2024You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projectscited by 45
  15. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 44
  16. 2025Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machinecited by 44
  17. 2025OrcaLoca: An LLM Agent Framework for Software Issue Localizationcited by 43
  18. 2024Human-In-the-Loop Software Development Agentscited by 42
  19. 2026DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Taskscited by 41
  20. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  21. 2024Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agentscited by 35
  22. 2025Evaluating Agent-based Program Repair at Googlecited by 35
  23. 2026SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolvingcited by 30
  24. 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Codecited by 28
  25. 2025Automated Benchmark Generation for Repository-Level Coding Taskscited by 27
  26. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Taskscited by 27
  27. 2025Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMscited by 24
  28. 2025Process-Centric Analysis of Agentic Software Systemscited by 24
  29. 2024PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedbackcited by 22
  30. 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verificationcited by 22
  31. 2025Issue Localization via LLM-Driven Iterative Code Graph Searchingcited by 22
  32. 2025SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugscited by 22
  33. 2025Large Language Model-based Data Science Agent: A Surveycited by 22
  34. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  35. 2025AgentBound: Securing Execution Boundaries of AI Agentscited by 20
  36. 2026BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?cited by 20
  37. 2025Agentic AI Software Engineers: Programming with Trustcited by 19
  38. 2025debug-gym: A Text-Based Environment for Interactive Debuggingcited by 19

50 most cited of 272 All 272 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MarsCode Agent: AI-native Automated Bug Fixing
  2. 2024SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer
  3. 2024Agent-Driven Automatic Software Improvement
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agents
  5. 2026SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents
  6. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixing
  7. 2025Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency
  8. 2025Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair