mlsanityData to 7 Oct 2026

MarsCode Agent: AI-native Automated Bug Fixing

arXiv 2409.00899 ↗First posted 2 Sep 2024cs.SE cs.AIcited by 68

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems. In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code. MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches. Our approach follows a systematic process of planning, bug reproduction, fault localization, candidate patch generation, and validation to ensure high-quality bug fixes. We evaluated MarsCode Agent on SWE-bench, a comprehensive benchmark of real-world software projects, and our results show that MarsCode Agent achieves a high success rate in bug fixing compared to most of the existing automated approaches.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 26 of its 51 references that are in the map. First posted on arXiv 2 Sep 2024.

Builds on

26 of 51 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  2. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  3. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May

Other references · 23

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  4. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  5. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  6. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  7. 2023Benchmarking Large Language Models for News Summarizationcited by 444
  8. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 325
  9. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  10. 2022Practical Program Repair in the Era of Large Pre-trained Language Modelscited by 133
  11. 2023Document-Level Machine Translation with Large Language Modelscited by 90
  12. 2023Impact of Code Language Models on Automated Program Repaircited by 85
11 more
  1. 2023Automatic Root Cause Analysis via Large Language Models for Cloud Incidentscited by 82
  2. 2023Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learningcited by 71
  3. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  4. 2023A Survey of Learning-based Automated Program Repaircited by 55
  5. 2024AgentFL: Scaling LLM-based Fault Localization to Project-Level Contextcited by 47
  6. 2023Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Modelscited by 38
  7. 2024Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuningcited by 30
  8. 2022DEAR: A Novel Deep Learning-based Approach for Automated Program Repaircited by 22
  9. 2023CCT5: A Code-Change-Oriented Pre-Trained Modelcited by 17
  10. 2024Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketchescited by 7
  11. 2023Enhancing Code Intelligence Tasks with ChatGPTcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 47; 2026: 13.

68 papers.

Sort:

By area:

  1. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  2. 2025Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scalingcited by 93
  3. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  4. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectoriescited by 75
  5. 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Taskscited by 69
  6. 2024Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvementcited by 57
  7. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  8. 2024You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projectscited by 45
  9. 2025OrcaLoca: An LLM Agent Framework for Software Issue Localizationcited by 43
  10. 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scalecited by 39
  11. 2025Evaluating Agent-based Program Repair at Googlecited by 35
  12. 2025MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluationcited by 32
38 more
  1. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Taskscited by 27
  2. 2025SWE-Dev: Building Software Engineering Agents with Training and Inference Scalingcited by 24
  3. 2025Process-Centric Analysis of Agentic Software Systemscited by 24
  4. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixingcited by 23
  5. 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verificationcited by 22
  6. 2025SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agentscited by 21
  7. 2025Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Taskscited by 20
  8. 2025SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Codecited by 17
  9. 2025CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent Systemcited by 15
  10. 2025An Empirical Study on Failures in Automated Issue Solvingcited by 15
  11. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic Systemcited by 15
  12. 2025Git Context Controller: Manage the Context of LLM-based Agents like Gitcited by 13
  13. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 13
  14. 2026Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agentscited by 13
  15. 2025Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Modelscited by 12
  16. 2024CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answeringcited by 11
  17. 2025Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixingcited by 11
  18. 2024LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issuescited by 10
  19. 2025Aime: Towards Fully-Autonomous Multi-Agent Frameworkcited by 9
  20. 2025Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systemscited by 8
  21. 2026AgentStepper: Interactive Debugging of Software Development Agentscited by 8
  22. 2024TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignmentcited by 7
  23. 2025Agent That Debugs: Dynamic State-Guided Vulnerability Repaircited by 7
  24. 2025InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolutioncited by 7
  25. 2025CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generationcited by 6
  26. 2025SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarkscited by 6
  27. 2025Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedbackcited by 6
  28. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  29. 2025PredicateFix: Repairing Static Analysis Alerts with Bridging Predicatescited by 5
  30. 2024Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repaircited by 4
  31. 2025EditLord: Learning Code Transformation Rules for Code Editingcited by 4
  32. 2025kAgent: An execution-guided crash resolution agent for the Linux kernelcited by 4
  33. 2025Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilitiescited by 4
  34. 2025Benchmarking LLMs for Fine-Grained Code Review with Enriched Context in Practicecited by 4
  35. 2025Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraphcited by 3
  36. 2025InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolutioncited by 3
  37. 2026EviACT: An Evidence-to-Action Framework for Agentic Program Repaircited by 3
  38. 2025ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulationscited by 2

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents
  2. 2024AutoCodeRover: Autonomous Program Improvement
  3. 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
  4. 2025SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs
  5. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
  6. 2025Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
  7. 2024Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios
  8. 2026Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports