# From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

arXiv: https://arxiv.org/abs/2410.08197 · HTML: https://mlsanity.com/paper/2410.08197/

## Key facts

- Cited by 46 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 49 of its 56 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 30 of 49)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://mlsanity.com/paper/2309.17452/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024)
- [AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls](https://mlsanity.com/paper/2402.04253/) (2024)
- [On the Tool Manipulation Capability of Open-source Large Language Models](https://mlsanity.com/paper/2305.16504/) (2023)
- [ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search](https://mlsanity.com/paper/2310.13227/) (2023)

## Built on by (most cited first, 30 of 46)

- [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025)
- [A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents](https://mlsanity.com/paper/2506.23844/) (2025)
- [Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents](https://mlsanity.com/paper/2510.02837/) (2025)
- [EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection](https://mlsanity.com/paper/2603.04900/) (2026)
- [MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments](https://mlsanity.com/paper/2506.01616/) (2025)
- [CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios](https://mlsanity.com/paper/2506.13977/) (2025)
- [ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering](https://mlsanity.com/paper/2510.20036/) (2025)
- [ToolFuzz -- Automated Agent Tool Testing](https://mlsanity.com/paper/2503.04479/) (2025)
- [PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play](https://mlsanity.com/paper/2503.14432/) (2025)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions](https://mlsanity.com/paper/2509.18847/) (2025)
- [ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning](https://mlsanity.com/paper/2504.01400/) (2025)
- [SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement](https://mlsanity.com/paper/2504.03561/) (2025)
- [Towards the Harness of Embodied Agents](https://mlsanity.com/paper/2608.11246/) (2026)
- [Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation](https://mlsanity.com/paper/2606.23127/) (2026)
- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning](https://mlsanity.com/paper/2503.03743/) (2025)
- [Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models](https://mlsanity.com/paper/2510.07248/) (2025)
- [SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents](https://mlsanity.com/paper/2604.07791/) (2026)
- [Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use](https://mlsanity.com/paper/2602.20426/) (2026)
- [From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents](https://mlsanity.com/paper/2607.07321/) (2026)
- [Task-Aligned Tool Recommendation for Large Language Models](https://mlsanity.com/paper/2411.09613/) (2024)
- [GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks](https://mlsanity.com/paper/2502.14848/) (2025)
- [PEToolLLM: Towards Personalized Tool Learning in Large Language Models](https://mlsanity.com/paper/2502.18980/) (2025)
- [Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors](https://mlsanity.com/paper/2512.13860/) (2025)
- [Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://mlsanity.com/paper/2601.07782/) (2026)
- [OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction](https://mlsanity.com/paper/2602.15197/) (2026)
- [Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration](https://mlsanity.com/paper/2604.18131/) (2026)

## Abstract (arXiv)

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical challenge of bridging the comprehension gap between LLMs and external tools due to the inadequacies and inaccuracies inherent in existing human-centric tool documentation. We propose a novel framework, DRAFT, aimed at Dynamically Refining tool documentation through the Analysis of Feedback and Trials emanating from LLMs' interactions with external tools. This methodology pivots on an innovative trial-and-error approach, consisting of three distinct learning phases: experience gathering, learning from experience, and documentation rewriting, to iteratively enhance the tool documentation. This process is further optimized by implementing a diversity-promoting exploration strategy to ensure explorative diversity and a tool-adaptive termination mechanism to prevent overfitting while enhancing efficiency. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality, fostering a deeper comprehension and more effective utilization of tools by LLMs. Notably, our analysis reveals that the tool documentation refined via our approach demonstrates robust cross-model generalization capabilities.