mlsanityData to 14 Oct 2026

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems

arXiv 2502.11098 ↗First posted 16 Feb 2025cs.AI cs.LG cs.MAcited by 17

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

Abstract (arXiv)

Recent advancements in LLM-based multi-agent (LLM-MA) systems have shown promise, yet significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose textitTalk Structurally, Act Hierarchically (TalkHier), a novel framework that introduces a structured communication protocol for context-rich exchanges and a hierarchical refinement system to address issues such as incorrect outputs, falsehoods, and biases. textitTalkHier surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse), and majority voting strategies on current LLM and single-agent baselines (e.g., ReAct, GPT4o), across diverse tasks, including open-domain question answering, domain-specific selective questioning, and practical advertisement text generation. These results highlight its potential to set a new standard for LLM-MA systems, paving the way for more effective, adaptable, and collaborative multi-agent frameworks. The code is available https://github.com/sony/talkhier.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 29 of its 46 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

29 of 46 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents31 Dec
  2. 2024LLM-based Multi-Agent Systems: Techniques and Business Perspectives21 Nov
  3. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  4. 2024Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models17 Jul
  5. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  6. 2024CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving26 Apr
  7. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?28 Feb
  8. 2024LLM Multi-Agent Systems: Challenges and Open Problems5 Feb
  9. 2024Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions2 Feb
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  11. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agent14 Jan
  12. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects7 Jan
5 more
  1. 2024LLM Harmony: Multi-Agent Communication for Problem Solving2 Jan
  2. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  5. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 12

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  5. 2024A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalistcited by 137
  6. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 90
  7. 2024Determinants of LLM-assisted Decision-Makingcited by 56
  8. 2023Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generationcited by 38
  9. 2023Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Taskscited by 24
  10. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
  11. 2024Multi-LLM Text Summarizationcited by 5
  12. 2021GrowSpace: Learning How to Shape Plantscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 9.

17 papers.

Sort:

By area:

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  2. 2025Latent Collaboration in Multi-Agent Systemscited by 73
  3. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  4. 2025Thought Communication in Multiagent Collaborationcited by 30
  5. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 15
  6. 2025CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMscited by 9
  7. 2026The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systemscited by 9
  8. 2025LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documentscited by 7
  9. 2026PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Trainingcited by 7
  10. 2026MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systemscited by 7
  11. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  12. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
5 more
  1. 2026StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systemscited by 5
  2. 2025WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluationcited by 3
  3. 2025A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentencescited by 0
  4. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0
  5. 2026Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
  2. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  3. 2025Modeling Response Consistency in Multi-Agent LLM Systems: A Comparative Analysis of Shared and Separate Context Approaches
  4. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  5. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoning
  6. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  7. 2025AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System
  8. 2025Literature Review Of Multi-Agent Debate For Problem-Solving