mlsanityData to 7 Oct 2026

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

arXiv 2402.04253 ↗First posted 6 Feb 2024cs.CLcited by 121

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

Abstract (arXiv)

We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries. We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries. AnyTool primarily incorporates three elements: an API retriever with a hierarchical structure, a solver aimed at resolving user queries using a selected set of API candidates, and a self-reflection mechanism, which re-activates AnyTool if the initial solution proves impracticable. AnyTool is powered by the function calling feature of GPT-4, eliminating the need for training external modules. We also revisit the evaluation protocol introduced by previous works and identify a limitation in this protocol that leads to an artificially high pass rate. By revising the evaluation protocol to better reflect practical application scenarios, we introduce an additional benchmark, termed AnyToolBench. Experiments across various datasets demonstrate the superiority of our AnyTool over strong baselines such as ToolLLM and a GPT-4 variant tailored for tool utilization. For instance, AnyTool outperforms ToolLLM by +35.4% in terms of average pass rate on ToolBench. Code will be available at https://github.com/dyabel/AnyTool.

Key facts. Cited by 121 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 26 of its 30 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

26 of 30 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  2. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  3. 2023Large Language Models as Tool Makers26 May
  4. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  5. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  6. 2023Tool Learning with Foundation Models17 Apr
  7. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs14 Apr
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  9. 2022TALM: Tool Augmented Language Models24 May

Other references · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  10. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  11. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  12. 2023Large Language Modelscited by 774
5 more
  1. 2024Self-Rewarding Language Modelscited by 654
  2. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  3. 2023Factuality Challenges in the Era of Large Language Modelscited by 125
  4. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  5. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 66

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 26; 2025: 44; 2026: 51.

121 papers.

Sort:

By area:

  1. 2024Tool Learning with Large Language Models: A Surveycited by 221
  2. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  3. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 152
  4. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  5. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  6. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 108
  7. 2024Beyond Browsing: API-Based Web Agentscited by 77
  8. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  9. 2026SkillRouter: Skill Routing for LLM Agents at Scalecited by 57
  10. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Usecited by 48
  11. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  12. 2024Octopus v2: On-device language model for super agentcited by 45
38 more
  1. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  2. 2024Tool-Planner: Task Planning with Clusters across Multiple Toolscited by 32
  3. 2025MCP-Zero: Active Tool Discovery for Autonomous LLM Agentscited by 32
  4. 2025InSTA: Towards Internet-Scale Training For Agentscited by 31
  5. 2024ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedbackcited by 28
  6. 2025API Agents vs. GUI Agents: Divergence and Convergencecited by 28
  7. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  8. 2024Octopus: On-device language model for function calling of software APIscited by 26
  9. 2025Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attributioncited by 25
  10. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  11. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  12. 2025TripTailor: A Real-World Benchmark for Personalized Travel Planningcited by 22
  13. 2025UItron: Foundational GUI Agent with Advanced Perception and Planningcited by 22
  14. 2026EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selectioncited by 22
  15. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  16. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Modelscited by 17
  17. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  18. 2025Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocationcited by 16
  19. 2024Learning Evolving Tools for Large Language Modelscited by 15
  20. 2025Graph RAG-Tool Fusioncited by 15
  21. 2025LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queriescited by 15
  22. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  23. 2026Benchmarking LLM Tool-Use in the Wildcited by 15
  24. 2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scalecited by 15
  25. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 14
  26. 2025From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agentscited by 14
  27. 2024Rethinking Generative Large Language Model Evaluation for Semantic Comprehensioncited by 13
  28. 2026ToolGate: Contract-Grounded and Verified Tool Execution for LLMscited by 13
  29. 2025Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Samplingcited by 12
  30. 2024ChatHuman: Chatting about 3D Humans with Toolscited by 11
  31. 2024EcoAct: Economic Agent Determines When to Register What Actioncited by 11
  32. 2025M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmarkcited by 11
  33. 2025AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoningcited by 11
  34. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  35. 2024PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Gamescited by 10
  36. 2024Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenariocited by 10
  37. 2024MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Callingcited by 10
  38. 2025Secure and Efficient Access Control for Computer-Use Agents via Context Spacecited by 10

50 most cited of 121 All 121 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
  2. 2026Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
  3. 2024NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls
  4. 2026VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
  5. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets
  6. 2025Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling
  7. 2025The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
  8. 2026Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models