mlsanityData to 14 Oct 2026

Making Language Models Better Tool Learners with Execution Feedback

arXiv 2305.13068 ↗First posted 22 May 2023cs.CL cs.AI cs.HCcited by 70

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Tools serve as pivotal interfaces that enable humans to understand and reshape the environment. With the advent of foundation models, AI systems can utilize tools to expand their capabilities and interact with the real world. Existing tool learning methodologies, encompassing supervised fine-tuning and prompt engineering approaches, often induce large language models to utilize tools indiscriminately, as complex tasks often exceed their own competencies. However, introducing tools for simple tasks, which the models themselves can readily resolve, can inadvertently propagate errors rather than enhance performance. This leads to the research question: can we teach language models when and how to use tools? To meet this need, we propose Tool leaRning wIth exeCution fEedback (TRICE), a two-stage end-to-end framework that enables the model to continually learn through feedback derived from tool execution, thereby learning when and how to use tools effectively. Experimental results, backed by further analysis, show that TRICE can make the large language model selectively use tools by improving the accuracy of tool usage while enhancing insufficient tool learning and mitigating excessive reliance on tools. Code is available at https://github.com/zjunlp/TRICE.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 40 of its 71 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

40 of 71 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  2. 2023Tool Learning with Foundation Models17 Apr
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2017Deep reinforcement learning from human preferencescited by 3,912
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  12. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
25 more
  1. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  2. 2019Language Models as Knowledge Bases?cited by 1,936
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  6. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  7. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  9. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  10. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 668
  11. 2018Behavioral Cloning from Observationcited by 492
  12. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 463
  13. 2016Solving General Arithmetic Word Problemscited by 360
  14. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356
  15. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  16. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 340
  17. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  18. 2022Reasoning with Language Model Prompting: A Surveycited by 252
  19. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221
  20. 2021Internet-Augmented Dialogue Generationcited by 217
  21. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  22. 2022Open-vocabulary Queryable Scene Representations for Real World Planningcited by 160
  23. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  24. 2022Mind's Eye: Grounded Language Model Reasoning through Simulationcited by 84
  25. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 25; 2025: 25; 2026: 9.

70 papers.

Sort:

By area:

  1. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  2. 2024Tool Learning with Large Language Models: A Surveycited by 223
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  4. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  5. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 158
  6. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  7. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 117
  8. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  9. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 100
  10. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  11. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 78
  12. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
38 more
  1. 2024Unified Hallucination Detection for Multimodal Large Language Modelscited by 75
  2. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  3. 2024Agent Planning with World Knowledge Modelcited by 70
  4. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  5. 2024LLM With Tools: A Surveycited by 61
  6. 2025TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Usecited by 51
  7. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  8. 2023ToolTalk: Evaluating Tool-Usage in a Conversational Settingcited by 45
  9. 2023OceanGPT: A Large Language Model for Ocean Science Taskscited by 43
  10. 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 43
  11. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  12. 2024LLMs Meet Multimodal Generation and Editing: A Surveycited by 35
  13. 2024Towards Uncertainty-Aware Language Agentcited by 32
  14. 2024ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedbackcited by 29
  15. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 23
  16. 2023Tool-Augmented Reward Modelingcited by 20
  17. 2024DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoningcited by 19
  18. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19
  19. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolutioncited by 17
  20. 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Modelscited by 17
  21. 2024Learning Evolving Tools for Large Language Modelscited by 16
  22. 2024CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planningcited by 14
  23. 2024SAUP: Situation Awareness Uncertainty Propagation on LLM Agentcited by 14
  24. 2025ProgCo: Program Helps Self-Correction of Large Language Modelscited by 14
  25. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  26. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 14
  27. 2023Large Knowledge Model: Perspectives and Challengescited by 12
  28. 2023InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Modelscited by 11
  29. 2024FLAP: Flow-Adhering Planning with Constrained Decoding in LLMscited by 11
  30. 2025SEM: Reinforcement Learning for Search-Efficient Large Language Modelscited by 9
  31. 2025Hell or High Water: Evaluating Agentic Recovery from External Failurescited by 9
  32. 2024How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Datacited by 8
  33. 2025DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Modelscited by 8
  34. 2025Self-Training Large Language Models for Tool-Use Without Demonstrationscited by 7
  35. 2025Dynamic Tool Dependency Retrieval for Lightweight Function Callingcited by 7
  36. 2026To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Callingcited by 7
  37. 2024Self-Steering Optimization: Autonomous Preference Optimization for Large Language Modelscited by 5
  38. 2025DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfercited by 5

50 most cited of 70 All 70 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
  2. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
  3. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  4. 2025ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
  5. 2025Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
  6. 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
  7. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
  8. 2025ToLeaP: Rethinking Development of Tool Learning with Large Language Models