mlsanityData to 7 Oct 2026

Executable Code Actions Elicit Better LLM Agents

arXiv 2402.01030 ↗First posted 1 Feb 2024cs.CL cs.AIcited by 537

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

Abstract (arXiv)

Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e.g., the scope of pre-defined tools) and restricted flexibility (e.g., inability to compose multiple tools). This work proposes to use executable Python code to consolidate LLM agents' actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark shows that CodeAct outperforms widely used alternatives (up to 20% higher success rate). The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language. To this end, we collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. We show that it can be used with existing data to improve models in agent-oriented tasks without compromising their general capability. CodeActAgent, finetuned from Llama2 and Mistral, is integrated with Python interpreter and uniquely tailored to perform sophisticated tasks (e.g., model training) using existing libraries and autonomously self-debug.

Key facts. Cited by 537 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 59 of its 134 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

59 of 134 references.

References · 59

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  8. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  10. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
38 more
  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  3. 2023Mistral 7Bcited by 3,065
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  12. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  13. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  14. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  15. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  16. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  17. 2023Teaching Large Language Models to Self-Debugcited by 963
  18. 2021Measuring Coding Challenge Competence With APPScited by 879
  19. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  20. 2022PAL: Program-aided Language Modelscited by 635
  21. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  22. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  23. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  24. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  25. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  26. 2023Augmented Language Models: a Surveycited by 398
  27. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  28. 2023Language Models can Solve Computer Taskscited by 371
  29. 2023Tool Learning with Foundation Modelscited by 302
  30. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  31. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  32. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  33. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  34. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  35. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  36. 2023GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Modelscited by 174
  37. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  38. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 78; 2025: 174; 2026: 285.

537 papers.

Sort:

By area:

  1. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  2. 2024A Survey on Large Language Models for Code Generationcited by 646
  3. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 306
  4. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 300
  5. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  6. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  7. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  8. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 196
  9. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  10. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 191
  11. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 174
  12. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
38 more
  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  2. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  4. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  5. 2025Progent: Securing AI Agents with Privilege Controlcited by 121
  6. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  7. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 102
  8. 2025Recursive Language Modelscited by 94
  9. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 93
  10. 2025Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoningcited by 88
  11. 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agentscited by 87
  12. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  13. 2024Beyond Browsing: API-Based Web Agentscited by 77
  14. 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulationcited by 72
  15. 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Taskscited by 69
  16. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agentscited by 66
  17. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  18. 2026Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scalecited by 65
  19. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  20. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  21. 2024Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Explorationcited by 58
  22. 2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Modelscited by 57
  23. 2024Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvementcited by 57
  24. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
  25. 2025Self-Challenging Language Model Agentscited by 56
  26. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  27. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  28. 2025OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflowscited by 54
  29. 2026Natural-Language Agent Harnessescited by 54
  30. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  31. 2025Training-Free Group Relative Policy Optimizationcited by 53
  32. 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningcited by 52
  33. 2024SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositoriescited by 52
  34. 2024EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilitiescited by 51
  35. 2025MiniCPM4: Ultra-Efficient LLMs on End Devicescited by 51
  36. 2026Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Frameworkcited by 50
  37. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  38. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49

50 most cited of 537 All 537 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024DynaSaur: Large Language Agents Beyond Predefined Actions
  2. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence
  3. 2025Every Software as an Agent: Blueprint and Case Study
  4. 2024Empowering Large Language Model Agents through Action Learning
  5. 2024Agents in Software Engineering: Survey, Landscape, and Vision
  6. 2026Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
  7. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
  8. 2025LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering