mlsanityData to 7 Oct 2026

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

arXiv 2305.14318 ↗First posted 23 May 2023cs.CLcited by 90

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems and diverse tabular contents. Remarkably, CREATOR outperforms existing chain-of-thought, program-of-thought, and tool-using baselines. Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability. Further research demonstrates that leveraging LLMs as tool creators facilitates knowledge transfer, and LLMs exhibit varying levels of tool creation abilities, enabling them to adapt to diverse situations. The tool creation ability revolutionizes the LLM's problem-solving paradigm, driving us closer to the next frontier of artificial intelligence. All the codes and data are released.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 31 of its 40 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

31 of 40 references.

References · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  12. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
19 more
  1. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  3. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  4. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  5. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  6. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  7. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  8. 2022PAL: Program-aided Language Modelscited by 635
  9. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  10. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  11. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  12. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  13. 2023Tool Learning with Foundation Modelscited by 302
  14. 2021Internet-Augmented Dialogue Generationcited by 217
  15. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 197
  16. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  17. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  18. 2022NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Flycited by 48
  19. 2023LeTI: Learning to Generate from Textual Interactionscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 23; 2025: 25; 2026: 37.

90 papers.

Sort:

By area:

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  4. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  5. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  6. 2024Tool Learning with Large Language Models: A Surveycited by 221
  7. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  8. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  9. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 191
  10. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 174
  11. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  12. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
38 more
  1. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  2. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 114
  3. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forwardcited by 105
  4. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  5. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  6. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  7. 2025Acting Less is Reasoning More! Teaching Model to Act Efficientlycited by 80
  8. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  9. 2024LLM With Tools: A Surveycited by 60
  10. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 51
  11. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  12. 2024Offline Training of Language Model Agents with Functions as Learnable Weightscited by 47
  13. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  14. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 32
  15. 2024InferCept: Efficient Intercept Support for Augmented Large Language Model Inferencecited by 32
  16. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  17. 2024DynaSaur: Large Language Agents Beyond Predefined Actionscited by 30
  18. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  19. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 29
  20. 2026SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?cited by 28
  21. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  22. 2023Mathematical Language Models: A Surveycited by 24
  23. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  24. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  25. 2025ToolRM: Outcome Reward Models for Tool-Calling Large Language Modelscited by 16
  26. 2025Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Usecited by 16
  27. 2025xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learningcited by 16
  28. 2026SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learningcited by 13
  29. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  30. 2026SEAL: Synergistic Co-Evolution of Agents and Learning Environmentscited by 9
  31. 2024Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Modelscited by 8
  32. 2025Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLMcited by 8
  33. 2024Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Librariescited by 7
  34. 2024Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptationcited by 7
  35. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 6
  36. 2026Hypothesis-Driven Skill Optimization for LLM Agentscited by 6
  37. 2025ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoningcited by 5
  38. 2026Generative Skill Composition for LLM Agentscited by 5

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Meta-Reasoning Improves Tool Use in Large Language Models
  2. 2023ART: Automatic multi-step reasoning and tool-use for large language models
  3. 2025Distilling Tool Knowledge into Language Models via Back-Translated Traces
  4. 2025From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models
  5. 2024Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
  6. 2025OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
  7. 2025Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
  8. 2025Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates