# ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback

arXiv: https://arxiv.org/abs/2409.14826 · HTML: https://mlsanity.com/paper/2409.14826/

## Key facts

- Cited by 29 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 20 of its 38 references that are in the map.
- First posted on arXiv 23 Sep 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, 20 of 20)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls](https://mlsanity.com/paper/2402.04253/) (2024)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [Making Language Models Better Tool Learners with Execution Feedback](https://mlsanity.com/paper/2305.13068/) (2023)
- [PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback](https://mlsanity.com/paper/2307.14936/) (2023)
- [TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems](https://mlsanity.com/paper/2311.11315/) (2023)
- [From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs](https://mlsanity.com/paper/2402.18157/) (2024)

## Built on by (most cited first, 29 of 29)

- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning](https://mlsanity.com/paper/2506.04625/) (2025)
- [CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning](https://mlsanity.com/paper/2506.07551/) (2025)
- [Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use](https://mlsanity.com/paper/2602.23368/) (2025)
- [TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation](https://mlsanity.com/paper/2505.20016/) (2025)
- [SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution](https://mlsanity.com/paper/2605.10114/) (2026)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection](https://mlsanity.com/paper/2510.18798/) (2025)
- [LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences](https://mlsanity.com/paper/2509.12273/) (2025)
- [ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"](https://mlsanity.com/paper/2508.04086/) (2025)
- [Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective](https://mlsanity.com/paper/2509.22613/) (2025)
- [PEToolLLM: Towards Personalized Tool Learning in Large Language Models](https://mlsanity.com/paper/2502.18980/) (2025)
- [ML-Tool-Bench: Tool-Augmented Planning for ML Tasks](https://mlsanity.com/paper/2512.00672/) (2025)
- [Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models](https://mlsanity.com/paper/2512.15089/) (2025)
- [Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems](https://mlsanity.com/paper/2602.14901/) (2026)
- [Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Model](https://mlsanity.com/paper/2604.07816/) (2026)
- [PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use](https://mlsanity.com/paper/2601.20439/) (2026)
- [GNNVerifier: Graph-based Verifier for LLM Task Planning](https://mlsanity.com/paper/2603.14730/) (2026)
- [GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support](https://mlsanity.com/paper/2604.12306/) (2026)
- [Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling](https://mlsanity.com/paper/2607.13558/) (2026)
- [AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits](https://mlsanity.com/paper/2608.03738/) (2026)
- [Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges](https://mlsanity.com/paper/2608.17605/) (2026)
- [What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review](https://mlsanity.com/paper/2609.33153/) (2026)
- [SWI: Speaking with Intent in Large Language Models](https://mlsanity.com/paper/2503.21544/) (2025)
- [Dual Engines of Thoughts: A Depth-Breadth Integration Framework for Open-Ended Analysis](https://mlsanity.com/paper/2504.07872/) (2025)
- [ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models](https://mlsanity.com/paper/2601.21947/) (2026)
- [MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents](https://mlsanity.com/paper/2609.24161/) (2026)
- [Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems](https://mlsanity.com/paper/2610.14736/) (2026)

## Abstract (arXiv)

Recently, tool-augmented LLMs have gained increasing attention. Given an instruction, tool-augmented LLMs can interact with various external tools in multiple rounds and provide a final answer. However, previous LLMs were trained on overly detailed instructions, which included API names or parameters, while real users would not explicitly mention these API details. This leads to a gap between trained LLMs and real-world scenarios. In addition, most works ignore whether the interaction process follows the instruction. To address these issues, we constructed a training dataset called MGToolBench, which contains statement and category-level instructions to better reflect real-world scenarios. In addition, we propose ToolPlanner, a two-stage reinforcement learning framework that utilizes path planning and two feedback mechanisms to enhance the LLM's task completion and instruction-following capabilities. Experimental results show that ToolPlanner significantly improves the Match Rate, Pass Rate and Win Rate by 26.8%, 20.2%, and 5.6% compared to the SOTA model. Human evaluation verifies that the multi-granularity instructions can better align with users' usage habits. Our data and code will be released upon acceptance.