mlsanityData to 7 Oct 2026

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent

arXiv 2401.07324 ↗First posted 14 Jan 2024cs.AI cs.CLcited by 92

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete various tasks in a self-directed fashion. The challenge of tool use demands that LLMs not only understand user queries and generate answers accurately but also excel in task planning, tool invocation, and result summarization. While traditional works focus on training a single LLM with all these capabilities, performance limitations become apparent, particularly with smaller models. To overcome these challenges, we propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability. To effectively train this framework, we introduce a two-stage training paradigm. First, we fine-tune a backbone LLM on the entire dataset without discriminating sub-tasks, providing the model with a comprehensive understanding of the task. Second, the fine-tuned LLM is used to instantiate the planner, caller, and summarizer respectively, which are continually fine-tuned on respective sub-tasks. Evaluation across various tool-use benchmarks illustrates that our proposed multi-LLM framework surpasses the traditional single-LLM approach, highlighting its efficacy and advantages in tool learning.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 26 of its 48 references that are in the map. First posted on arXiv 14 Jan 2024.

Builds on

26 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Experiential Co-Learning of Software-Developing Agents28 Dec
  2. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  3. 2023FireAct: Toward Language Agent Fine-tuning9 Oct
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  5. 2023Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models26 Apr

Other references · 21

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  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. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
9 more
  1. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  2. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  3. 2023Tool Learning with Foundation Modelscited by 302
  4. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  5. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  6. 2021ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learningcited by 253
  7. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  8. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 222
  9. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 33; 2025: 33; 2026: 26.

92 papers.

Sort:

By area:

  1. 2024Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perceptioncited by 283
  2. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
  3. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  4. 2024Tool Learning with Large Language Models: A Surveycited by 221
  5. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 187
  6. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  7. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  8. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  9. 2025Agentic Large Language Models, a surveycited by 105
  10. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  11. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 80
  12. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
38 more
  1. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 72
  2. 2024Agent Planning with World Knowledge Modelcited by 66
  3. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 63
  4. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  5. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
  6. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  7. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
  8. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  9. 2025TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Usecited by 46
  10. 2024Octopus v2: On-device language model for super agentcited by 45
  11. 2024Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligencecited by 27
  12. 2024Octopus: On-device language model for function calling of software APIscited by 26
  13. 2024Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Taskscited by 23
  14. 2024BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysiscited by 20
  15. 2024BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Taskscited by 19
  16. 2025Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systemscited by 17
  17. 2025Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocationcited by 16
  18. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 15
  19. 2024Learning Evolving Tools for Large Language Modelscited by 15
  20. 2025Guiding Reasoning in Small Language Models with LLM Assistancecited by 13
  21. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  22. 2025Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflowscited by 10
  23. 2026LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agentscited by 10
  24. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinementcited by 9
  25. 2025HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistantscited by 9
  26. 2026AgenTRIM: Tool Risk Mitigation for Agentic AIcited by 9
  27. 2026MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolutioncited by 8
  28. 2024CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performancecited by 6
  29. 2026ICaRus: Identical Cache Reuse for Efficient Multi Model Inferencecited by 6
  30. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  31. 2024AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learningcited by 5
  32. 2025LLM-Agent-Controller: A Universal Multi-Agent Large Language Model System as a Control Engineercited by 5
  33. 2025AlphaApollo: A System for Deep Agentic Reasoningcited by 5
  34. 2026PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agentscited by 5
  35. 2024RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domaincited by 4
  36. 2024Conversational Medical AI: Ready for Practicecited by 4
  37. 2026FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environmentscited by 4
  38. 2024Human-Centered LLM-Agent User Interface: A Position Papercited by 3

50 most cited of 92 All 92 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024LLM With Tools: A Survey
  2. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
  3. 2023Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub
  4. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
  5. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
  6. 2026SAGE: Tool-Augmented LLM Task Solving Strategies in Scalable Multi-Agent Environments
  7. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
  8. 2026Multi-User Large Language Model Agents