mlsanityData to 13 Oct 2026

Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum

arXiv 2308.14034 ↗First posted 27 Aug 2023cs.AI cs.CLcited by 64

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

Abstract (arXiv)

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although some works employ open-source LLMs for the tool learning task, most of them are trained in a controlled environment in which LLMs only learn to execute the human-provided tools. However, selecting proper tools from the large toolset is also a crucial ability for the tool learning model to be applied in real-world applications. Existing methods usually directly employ self-instruction methods to train the model, which ignores differences in tool complexity. In this paper, we propose the Confucius, a novel tool learning framework to train LLM to use complicated tools in real-world scenarios, which contains two main phases: (1) We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum; (2) thenceforth, we propose the Iterative Self-instruct from Introspective Feedback (ISIF) to dynamically construct the dataset to improve the ability to use the complicated tool. Extensive experiments conducted on both controlled and real-world settings demonstrate the superiority of our tool learning framework in the real-world application scenarios compared to both tuning-free (e.g. ChatGPT, Claude) and tuning-based baselines (e.g. GPT4Tools).

Key facts. Cited by 64 papers in the map (data through 13 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 24 of its 45 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

24 of 45 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  2. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  3. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  4. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  5. 2023Tool Learning with Foundation Models17 Apr
  6. 2023ART: Automatic multi-step reasoning and tool-use for large language models16 Mar
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 17

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,502
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,736
  5. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,180
  6. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,120
  7. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,029
  8. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 663
  9. 2022PAL: Program-aided Language Modelscited by 647
  10. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 515
  11. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 397
  12. 2023Language Models can Solve Computer Taskscited by 371
5 more
  1. 2023The False Promise of Imitating Proprietary LLMscited by 258
  2. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  3. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 116
  4. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  5. 2019Product-Aware Answer Generation in E-Commerce Question-Answeringcited by 27

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 2; 2024: 20; 2025: 31; 2026: 11.

64 papers.

Sort:

By area:

  1. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 279
  2. 2024Tool Learning with Large Language Models: A Surveycited by 221
  3. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 152
  4. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 123
  5. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 81
  6. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoningcited by 69
  7. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 62
  8. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
  9. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  10. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  11. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  12. 2025SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Datacited by 50
38 more
  1. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  2. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  3. 2025Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Modelscited by 46
  4. 2025DeepShop: A Benchmark for Deep Research Shopping Agentscited by 44
  5. 2024From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injectioncited by 38
  6. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 36
  7. 2024I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigmcited by 27
  8. 2024Simulating Financial Market via Large Language Model based Agentscited by 25
  9. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Modelscited by 17
  10. 2023Instruction Tuning with Human Curriculumcited by 15
  11. 2024FLAP: Flow-Adhering Planning with Constrained Decoding in LLMscited by 11
  12. 2025GTool: Graph Enhanced Tool Planning with Large Language Modelcited by 10
  13. 2025GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulationcited by 9
  14. 2025TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluationcited by 9
  15. 2025iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Usecited by 7
  16. 2025PDE-Agent: A toolchain-augmented multi-agent framework for PDE solvingcited by 7
  17. 2024CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performancecited by 6
  18. 2024LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architecturescited by 5
  19. 2024TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLMcited by 5
  20. 2025Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessmentcited by 5
  21. 2025AlphaApollo: A System for Deep Agentic Reasoningcited by 5
  22. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  23. 2024What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworkscited by 4
  24. 2025Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Frameworkcited by 4
  25. 2026Agentic Tool Use in Large Language Modelscited by 4
  26. 2026PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Modelscited by 4
  27. 2024Human-Centered LLM-Agent User Interface: A Position Papercited by 3
  28. 2024Task-Aligned Tool Recommendation for Large Language Modelscited by 3
  29. 2025Unify Graph Learning with Text: Unleashing LLM Potentials for Session Searchcited by 3
  30. 2025NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestrationcited by 3
  31. 2025MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Modelscited by 3
  32. 2025Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understandingcited by 3
  33. 2025ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learningcited by 3
  34. 2025Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templatescited by 3
  35. 2025Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editorscited by 3
  36. 2025Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidancecited by 2
  37. 2026Beyond Single-Shot: Multi-step Tool Retrieval via Query Planningcited by 2
  38. 2026Multi-Field Tool Retrievalcited by 2

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025ToLeaP: Rethinking Development of Tool Learning with Large Language Models
  2. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  3. 2024LLM With Tools: A Survey
  4. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
  5. 2025Self-Training Large Language Models for Tool-Use Without Demonstrations
  6. 2023Making Language Models Better Tool Learners with Execution Feedback
  7. 2024LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
  8. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph