mlsanityData to 7 Oct 2026

ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph

arXiv 2403.00839 ↗First posted 29 Feb 2024cs.AI cs.CLcited by 59

Not on the map. Why?

Cited by 40 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

While achieving remarkable progress in a broad range of tasks, large language models (LLMs) remain significantly limited in properly using massive external tools. Existing in-context learning approaches simply format tools into a list of plain text descriptions and input them to LLMs, from which, LLMs generate a sequence of tool calls to solve problems step by step. Such a paradigm ignores the intrinsic dependency between tools and offloads all reasoning loads to LLMs, making them restricted to a limited number of specifically designed tools. It thus remains challenging for LLMs to operate on a library of massive tools, casting a great limitation when confronted with real-world scenarios. This paper proposes ToolNet, a plug-and-play framework that scales up the number of tools to thousands with a moderate increase in token consumption. ToolNet organizes tools into a directed graph. Each node represents a tool, and weighted edges denote tool transition. Starting from an initial tool node, an LLM navigates in the graph by iteratively choosing the next one from its successors until the task is resolved. Extensive experiments show that ToolNet can achieve impressive results in challenging multi-hop tool learning datasets and is resilient to tool failures.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

24 of 36 references.

References · 24

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  12. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
12 more
  1. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  2. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  3. 2023Augmented Language Models: a Surveycited by 398
  4. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  5. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  6. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 278
  7. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  8. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  9. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 190
  10. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  11. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 67
  12. 2021Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?cited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 24; 2026: 25.

59 papers.

Sort:

By area:

  1. 2024Tool Learning with Large Language Models: A Surveycited by 221
  2. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  3. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  4. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 53
  5. 2024Can Graph Learning Improve Planning in LLM-based Agents?cited by 42
  6. 2025SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integrationcited by 40
  7. 2026Code as Agent Harnesscited by 40
  8. 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Modelscited by 34
  9. 2026GraSP: Graph-Structured Skill Compositions for LLM Agentscited by 25
  10. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  11. 2024StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learningcited by 22
  12. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filteringcited by 19
38 more
  1. 2024ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Modelscited by 18
  2. 2026ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruningcited by 18
  3. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  4. 2025Graph RAG-Tool Fusioncited by 15
  5. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  6. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  7. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  8. 2024To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactionscited by 10
  9. 2024Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Pathcited by 10
  10. 2025MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Modelscited by 9
  11. 2025AutoTool: Efficient Tool Selection for Large Language Model Agentscited by 9
  12. 2026Group of Skills: Group-Structured Skill Retrieval for Agent Skill Librariescited by 9
  13. 2025GTool: Graph Enhanced Tool Planning with Large Language Modelcited by 7
  14. 2025Dynamic Tool Dependency Retrieval for Lightweight Function Callingcited by 7
  15. 2026ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Webcited by 7
  16. 2025Affordable AI Assistants with Knowledge Graph of Thoughtscited by 6
  17. 2025Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memorycited by 6
  18. 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planningcited by 6
  19. 2024FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planningcited by 5
  20. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  21. 2025Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systemscited by 4
  22. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  23. 2025NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestrationcited by 3
  24. 2025LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrievalcited by 3
  25. 2026CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrievalcited by 3
  26. 2024Building Multi-Agent Copilot towards Autonomous Agricultural Data Management and Analysiscited by 2
  27. 2025RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoningcited by 2
  28. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  29. 2026Multi-Field Tool Retrievalcited by 2
  30. 2026TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifierscited by 2
  31. 2026RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agentscited by 2
  32. 2026IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignmentcited by 2
  33. 2024SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended textcited by 1
  34. 2024Action Engine: Automatic Workflow Generation in FaaScited by 1
  35. 2025Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planningcited by 1
  36. 2025In-N-Out: A Parameter-Level API Graph Dataset for Tool Agentscited by 1
  37. 2026GNNVerifier: Graph-based Verifier for LLM Task Planningcited by 1
  38. 2026Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agentscited by 1

50 most cited of 59 All 59 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  2. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  3. 2023Structural Embeddings of Tools for Large Language Models
  4. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution
  5. 2023Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
  6. 2025Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists
  7. 2024WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models
  8. 2024LLM With Tools: A Survey