mlsanityData to 7 Oct 2026

Learning to Use Tools via Cooperative and Interactive Agents

arXiv 2403.03031 ↗First posted 5 Mar 2024cs.CLcited by 54

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

Abstract (arXiv)

Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution results into the next action prediction. Despite their progress, these methods suffer from performance degradation when addressing practical tasks due to: (1) the pre-defined pipeline with restricted flexibility to calibrate incorrect actions, and (2) the struggle to adapt a general LLM-based agent to perform a variety of specialized actions. To mitigate these problems, we propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. ConAgents introduces two communication protocols to enable the flexible cooperation of agents. To effectively generalize the ConAgents into open-source models, we also propose specialized action distillation, enhancing their ability to perform specialized actions in our framework. Our extensive experiments on three datasets show that the LLMs, when equipped with the ConAgents, outperform baselines with substantial improvement (i.e., up to 14% higher success rate).

Key facts. Cited by 54 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 40 of its 69 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

40 of 69 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages16 Feb
  2. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  3. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback19 Sep
  4. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum27 Aug
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  6. 2023ToolQA: A Dataset for LLM Question Answering with External Tools23 Jun
  7. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  8. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  9. 2023Large Language Models as Tool Makers26 May
  10. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  11. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 28

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  7. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  11. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
16 more
  1. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  2. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  3. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
  4. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  5. 2023Language Models can Solve Computer Taskscited by 371
  6. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  7. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  8. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  9. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  10. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  11. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systemscited by 116
  12. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 115
  13. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  14. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  15. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  16. 2023Experiential Co-Learning of Software-Developing Agentscited by 57

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 28; 2026: 15.

54 papers.

Sort:

By area:

  1. 2024Tool Learning with Large Language Models: A Surveycited by 221
  2. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  3. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  4. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  6. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  7. 2024MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPscited by 45
  8. 2025DeepShop: A Benchmark for Deep Research Shopping Agentscited by 42
  9. 2025LLM-based Human Simulations Have Not Yet Been Reliablecited by 30
  10. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  11. 2025Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysiscited by 27
  12. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 26
38 more
  1. 2025Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learningcited by 22
  2. 2025Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocationcited by 16
  3. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 15
  4. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 15
  5. 2025LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queriescited by 15
  6. 2025ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Modelscited by 8
  7. 2025Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLMcited by 8
  8. 2024Reasoning and Tools for Human-Level Forecastingcited by 7
  9. 2025iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Usecited by 7
  10. 2025Advancing and Benchmarking Personalized Tool Invocation for LLMscited by 7
  11. 2025Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklistscited by 7
  12. 2024SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generationcited by 5
  13. 2024TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLMcited by 5
  14. 2026VideoAgent: All-in-One Framework for Video Understanding and Editingcited by 5
  15. 2024What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworkscited by 4
  16. 2025Building LLM Agents by Incorporating Insights from Computer Systemscited by 4
  17. 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanismcited by 4
  18. 2025PEToolLLM: Towards Personalized Tool Learning in Large Language Modelscited by 3
  19. 2025Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editorscited by 3
  20. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  21. 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Usecited by 3
  22. 2025TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Modelscited by 2
  23. 2025AI Agents Should be Regulated Based on the Extent of Their Autonomous Operationscited by 2
  24. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2
  25. 2026Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systemscited by 2
  26. 2026IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignmentcited by 2
  27. 2025ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Modelscited by 1
  28. 2025Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systemscited by 1
  29. 2026Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agentscited by 1
  30. 2026Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Callscited by 1
  31. 2026DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agentscited by 1
  32. 2026AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuitscited by 1
  33. 2026Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agentscited by 1
  34. 2025Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Webcited by 0
  35. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlerscited by 0
  36. 2025TAPS: Tool-Augmented Personalisation via Structured Taggingcited by 0
  37. 2025Towards Reliable Multi-Agent Systems for Marketing Applications via Reflection, Memory, and Planningcited by 0
  38. 2025OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Modelscited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
  2. 2026Agentic Tool Use in Large Language Models
  3. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
  4. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
  5. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs
  6. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
  7. 2026OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
  8. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users