mlsanityData to 7 Oct 2026

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

arXiv 2409.14826 ↗First posted 23 Sep 2024cs.CL cs.AIcited by 28

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

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.

Key facts. Cited by 28 papers in the map (data through 7 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.

Builds on

20 of 38 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls6 Feb
  2. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback19 Sep
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  4. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  5. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  6. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  7. 2023Making Language Models Better Tool Learners with Execution Feedback22 May
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 12

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  6. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  7. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  8. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  9. 2023RLTF: Reinforcement Learning from Unit Test Feedbackcited by 110
  10. 2023PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedbackcited by 69
  11. 2023TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systemscited by 39
  12. 2024From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 15; 2026: 12.

28 papers.

Sort:

By area:

  1. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 72
  2. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  3. 2025Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learningcited by 22
  4. 2025CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learningcited by 12
  5. 2025Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool usecited by 10
  6. 2025TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluationcited by 9
  7. 2026SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Executioncited by 8
  8. 2025What Makes a Good Natural Language Prompt?cited by 6
  9. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflectioncited by 6
  10. 2025LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferencescited by 5
  11. 2025ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"cited by 4
  12. 2025Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspectivecited by 4
16 more
  1. 2025PEToolLLM: Towards Personalized Tool Learning in Large Language Modelscited by 3
  2. 2025ML-Tool-Bench: Tool-Augmented Planning for ML Taskscited by 3
  3. 2025Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Modelscited by 2
  4. 2026Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systemscited by 2
  5. 2026PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Usecited by 1
  6. 2026GNNVerifier: Graph-based Verifier for LLM Task Planningcited by 1
  7. 2026Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Modelcited by 1
  8. 2026GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Supportcited by 1
  9. 2026Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profilingcited by 1
  10. 2026AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuitscited by 1
  11. 2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
  12. 2025SWI: Speaking with Intent in Large Language Modelscited by 0
  13. 2025Dual Engines of Thoughts: A Depth-Breadth Integration Framework for Open-Ended Analysiscited by 0
  14. 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Modelscited by 0
  15. 2026MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agentscited by 0
  16. 2026What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Reviewcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
  2. 2024LLM With Tools: A Survey
  3. 2025Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
  4. 2026Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs
  5. 2025ToolExpander: Extending the Frontiers of Tool-Using Reinforcement Learning to Weak LLMs
  6. 2024StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning
  7. 2025Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
  8. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning