mlsanityData to 7 Oct 2026

CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models

arXiv 2404.01663 ↗First posted 2 Apr 2024cs.CL cs.AI cs.CCcited by 26

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

Abstract (arXiv)

Open large language models (LLMs) have significantly advanced the field of natural language processing, showcasing impressive performance across various tasks.Despite the significant advancements in LLMs, their effective operation still relies heavily on human input to accurately guide the dialogue flow, with agent tuning being a crucial optimization technique that involves human adjustments to the model for better response to such guidance.Addressing this dependency, our work introduces the TinyAgent model, trained on a meticulously curated high-quality dataset. We also present the Collaborative Multi-Agent Tuning (CMAT) framework, an innovative system designed to augment language agent capabilities through adaptive weight updates based on environmental feedback. This framework fosters collaborative learning and real-time adaptation among multiple intelligent agents, enhancing their context-awareness and long-term memory. In this research, we propose a new communication agent framework that integrates multi-agent systems with environmental feedback mechanisms, offering a scalable method to explore cooperative behaviors. Notably, our TinyAgent-7B model exhibits performance on par with GPT-3.5, despite having fewer parameters, signifying a substantial improvement in the efficiency and effectiveness of LLMs.

Key facts. Cited by 26 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 30 of its 81 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

30 of 81 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning22 Dec
  2. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  3. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  4. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  10. 2020Knowledge Distillation: A Surveycited by 1,578
  11. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  12. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
14 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  3. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  4. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  5. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  6. 2017Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracycited by 100
  7. 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 95
  8. 2023Data Distillation: A Surveycited by 86
  9. 2021Adaptive Semiparametric Language Modelscited by 83
  10. 2021A linearized framework and a new benchmark for model selection for fine-tuningcited by 41
  11. 2021A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guaranteecited by 16
  12. 2020Selecting Informative Contexts Improves Language Model Finetuningcited by 11
  13. 2018Cross-Modal Attentional Context Learning for RGB-D Object Detectioncited by 4
  14. 2015Periodic Event-Triggered Synchronization of Linear Multi-agent Systems with Communication Delayscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 8; 2025: 18.

26 papers.

Sort:

By area:

  1. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 63
  2. 2024Self-evolving Agents with reflective and memory-augmented abilitiescited by 52
  3. 2024AI PERSONA: Towards Life-long Personalization of LLMscited by 30
  4. 2024Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generationcited by 29
  5. 2025Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Modelscited by 29
  6. 2025GraphRAG under Firecited by 23
  7. 2024A Survey on Large Language Model-based Agents for Statistics and Data Sciencecited by 22
  8. 2024Efficient Fine-Tuning of Large Language Models for Automated Medical Documentationcited by 16
  9. 2025Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategycited by 16
  10. 20251-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoningcited by 16
  11. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  12. 2025Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalizationcited by 11
14 more
  1. 2025ForgetMe: Evaluating Selective Forgetting in Generative Modelscited by 11
  2. 2024FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization systemcited by 8
  3. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  4. 2024A GEN AI Framework for Medical Note Generationcited by 6
  5. 2025MARS: Memory-Enhanced Agents with Reflective Self-improvementcited by 2
  6. 2025Industrial Internet Robot Collaboration System and Edge Computing Optimizationcited by 2
  7. 2025Training-Free Multimodal Large Language Model Orchestrationcited by 2
  8. 2025TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generationcited by 1
  9. 2025Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reportscited by 1
  10. 2025Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERTcited by 0
  11. 2025OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understandingcited by 0
  12. 2025AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Methodcited by 0
  13. 2025Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkerscited by 0
  14. 2025A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecturecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Can Small Agents Collaborate to Beat a Single Large Language Model?
  2. 2023Adapting LLM Agents with Universal Feedback in Communication
  3. 2025MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language
  4. 2024Adaptive In-conversation Team Building for Language Model Agents
  5. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
  6. 2025Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
  7. 2025LLM-Agent-Controller: A Universal Multi-Agent Large Language Model System as a Control Engineer
  8. 2024ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration