mlsanityData to 7 Oct 2026

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

arXiv 2409.16299 ↗First posted 9 Sep 2024cs.SE cs.AIcited by 61

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

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines.

Key facts. Cited by 61 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 65 of its 88 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

65 of 88 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents13 Aug
  2. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  3. 2024MASAI: Modular Architecture for Software-engineering AI Agents17 Jun
  4. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving18 May
  5. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  6. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar
  7. 2024Executable Code Actions Elicit Better LLM Agents1 Feb
  8. 2023ChatDev: Communicative Agents for Software Development16 Jul

Other references · 57

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  8. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  9. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2023Teaching Large Language Models to Self-Debugcited by 963
  12. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
38 more
  1. 2021Measuring Coding Challenge Competence With APPScited by 879
  2. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  3. 2023StarCoder: may the source be with you!cited by 790
  4. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  5. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  6. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  7. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  8. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  9. 2022CodeT: Code Generation with Generated Testscited by 369
  10. 2022A Systematic Evaluation of Large Language Models of Codecited by 360
  11. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
  12. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  13. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  14. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  15. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 242
  16. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  17. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 220
  18. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  19. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  20. 2023SantaCoder: don't reach for the stars!cited by 169
  21. 2023ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generationcited by 166
  22. 2016DeepCoder: Learning to Write Programscited by 145
  23. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  24. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  25. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
  26. 2024DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositoriescited by 71
  27. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  28. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  29. 2023A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localizationcited by 50
  30. 2024AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodologycited by 45
  31. 2022MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languagescited by 41
  32. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  33. 2024BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studiescited by 35
  34. 2022SelfAPR: Self-supervised Program Repair with Test Execution Diagnosticscited by 33
  35. 2024An Empirical Evaluation of LLMs for Solving Offensive Security Challengescited by 33
  36. 2023CodeTF: One-stop Transformer Library for State-of-the-art Code LLMscited by 21
  37. 2020TreeCaps: Tree-Based Capsule Networks for Source Code Processingcited by 16
  38. 2023ITER: Iterative Neural Repair for Multi-Location Patchescited by 16

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 25; 2026: 32.

61 papers.

Sort:

By area:

  1. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  2. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  3. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  4. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  5. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  6. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  7. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  8. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  9. 2025UTBoost: Rigorous Evaluation of Coding Agents on SWE-Benchcited by 44
  10. 2025OrcaLoca: An LLM Agent Framework for Software Issue Localizationcited by 43
  11. 2026Code as Agent Harnesscited by 40
  12. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 31
38 more
  1. 2025SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugscited by 22
  2. 2025Large Language Model-based Data Science Agent: A Surveycited by 22
  3. 2024CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMscited by 18
  4. 2026Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedcited by 18
  5. 2026Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agentscited by 17
  6. 2025Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanismcited by 16
  7. 2025AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenancecited by 15
  8. 2026AIDev: Studying AI Coding Agents on GitHubcited by 15
  9. 2026Coding Agents are Effective Long-Context Processorscited by 11
  10. 2026How to Interpret Agent Behaviorcited by 8
  11. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  12. 2025BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimizationcited by 7
  13. 2025An LLM-based multi-agent framework for agile effort estimationcited by 6
  14. 2025Automating Structural Engineering Workflows with Large Language Model Agentscited by 6
  15. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  16. 2026Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineeringcited by 6
  17. 2025ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planningcited by 5
  18. 2025Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Codecited by 5
  19. 2024Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulationcited by 4
  20. 2025Code Reasoning for Software Engineering Tasks: A Survey and A Call to Actioncited by 4
  21. 2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolutioncited by 4
  22. 2026FastContext: Training Efficient Repository Explorer for Coding Agentscited by 4
  23. 2024VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoningcited by 3
  24. 2025From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Contextcited by 3
  25. 2026SWE-Edit: Rethinking Code Editing for Efficient SWE-Agentcited by 3
  26. 2026AgentCollabBench: Diagnosing When Good Agents Make Bad Collaboratorscited by 3
  27. 2026A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAXcited by 2
  28. 2026Agentic Coding Needs Proactivity, Not Just Autonomycited by 2
  29. 2025From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Frameworkcited by 1
  30. 2025Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Trainingcited by 1
  31. 2026Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspectivecited by 1
  32. 2026Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitationscited by 1
  33. 2026Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentationcited by 1
  34. 2026Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolutioncited by 1
  35. 2026Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Searchcited by 1
  36. 2026Observability and Fault Injection for LLM-Based Multi-Agent Systems in Software Engineeringcited by 1
  37. 2025Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Supportcited by 0
  38. 2026Can Small Agents Collaborate to Beat a Single Large Language Model?cited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  2. 2025RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring
  3. 2025Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
  4. 2025Unified Software Engineering Agent as AI Software Engineer
  5. 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
  6. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents
  7. 2026ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
  8. 2024TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment