mlsanityData to 7 Oct 2026

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

arXiv 2405.15793 ↗First posted 6 May 2024cs.SE cs.AI cs.CLcited by 1,628

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

Abstract (arXiv)

Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively, far exceeding the previous state-of-the-art achieved with non-interactive LMs. Finally, we provide insight on how the design of the ACI can impact agents' behavior and performance.

Key facts. Cited by 1,628 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 6 of its 71 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

6 of 71 references.

References · 6

  1. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  2. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  3. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 175
  4. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  5. 2023WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuningcited by 42
  6. 2018Entropy Guided Spectrum Based Bug Localization Using Statistical Language Modelcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 95; 2025: 400; 2026: 1133.

1,628 papers.

Sort:

By area:

  1. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  2. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
  3. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  5. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  6. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 300
  7. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  8. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 291
  9. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 289
  10. 2025SWE-smith: Scaling Data for Software Engineering Agentscited by 255
  11. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  12. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
38 more
  1. 2024TextGrad: Automatic "Differentiation" via Textcited by 250
  2. 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolutioncited by 246
  3. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 236
  4. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  5. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
  6. 2025KernelBench: Can LLMs Write Efficient GPU Kernels?cited by 206
  7. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 205
  8. 2024AI Agents That Mattercited by 199
  9. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
  10. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  11. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  12. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  13. 2025Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingcited by 165
  14. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 162
  15. 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoningcited by 158
  16. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 155
  17. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  18. 2024Tree Search for Language Model Agentscited by 148
  19. 2024RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learningcited by 146
  20. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  21. 2025R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agentscited by 140
  22. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  23. 2025Towards a Science of Scaling Agent Systemscited by 125
  24. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  25. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 122
  26. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  27. 2026Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnessescited by 119
  28. 2024CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmarkcited by 115
  29. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 111
  30. 2025OS-Harm: A Benchmark for Measuring Safety of Computer Use Agentscited by 104
  31. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  32. 2025PromptArmor: Simple yet Effective Prompt Injection Defensescited by 98
  33. 2025Establishing Best Practices for Building Rigorous Agentic Benchmarkscited by 94
  34. 2024Teams of LLM Agents can Exploit Zero-Day Vulnerabilitiescited by 93
  35. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 93
  36. 2025Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scalingcited by 93
  37. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  38. 2025CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilitiescited by 90

50 most cited of 1,628 All 1,628 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
  2. 2024Agents in Software Engineering: Survey, Landscape, and Vision
  3. 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
  4. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  5. 2025Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild
  6. 2026SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration
  7. 2025Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
  8. 2026SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?