Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- URL: http://arxiv.org/abs/2502.11098v1
- Date: Sun, 16 Feb 2025 12:26:58 GMT
- Title: Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- Authors: Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, Shingo Takamatsu,
- Abstract summary: textitTalk Structurally, Act Hierarchically (TalkHier) is a novel framework that introduces a structured communication protocol for context-rich exchanges.<n>textitTalkHier surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse)
- Score: 10.67359331022116
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 \textit{Talk 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. \textit{TalkHier} 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.
Related papers
- Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems [0.8437187555622164]
Large language model (LLM) agents have shown increasing promise for collaborative task completion.<n>Existing multi-agent frameworks often rely on static, fixed roles, and limited inter-agent communication.<n>This paper proposes a coordination framework that enables adaptiveness through three core mechanisms.
arXiv Detail & Related papers (2025-07-22T22:42:51Z) - AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis [0.0]
We present a pilot study of AgentMaster, a novel modular multi-protocol MAS framework with self-implemented A2A and MCP.<n>The system supports natural language interaction without prior technical expertise and responds to multimodal queries.<n>Overall, our proposed framework contributes to the potential capabilities of domain-specific, cooperative, and scalable conversational AI powered by MAS.
arXiv Detail & Related papers (2025-07-08T03:34:26Z) - AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [70.60422261117816]
We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
arXiv Detail & Related papers (2025-06-21T18:34:43Z) - Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems [4.683612295430957]
This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept.<n>We propose a trainable agent framework called Agent-UniRAG for unified retrieval-augmented LLM systems.<n>The main idea is to design an LLM agent framework to solve RAG tasks step-by-step based on the complexity of the inputs.
arXiv Detail & Related papers (2025-05-28T16:46:31Z) - MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents [59.825725526176655]
Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents.
Existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
We introduce MultiAgentBench, a benchmark designed to evaluate LLM-based multi-agent systems across diverse, interactive scenarios.
arXiv Detail & Related papers (2025-03-03T05:18:50Z) - When One LLM Drools, Multi-LLM Collaboration Rules [98.71562711695991]
We argue for multi-LLM collaboration to better represent the extensive diversity of data, skills, and people.<n>We organize existing multi-LLM collaboration methods into a hierarchy, based on the level of access and information exchange.<n>We envision multi-LLM collaboration as an essential path toward compositional intelligence and collaborative AI development.
arXiv Detail & Related papers (2025-02-06T21:13:44Z) - LITA: An Efficient LLM-assisted Iterative Topic Augmentation Framework [0.0]
Large language models (LLMs) offer potential for dynamic topic refinement and discovery, yet their application often incurs high API costs.
To address these challenges, we propose the LLM-assisted Iterative Topic Augmentation framework (LITA)
LITA integrates user-provided seeds with embedding-based clustering and iterative refinement.
arXiv Detail & Related papers (2024-12-17T01:43:44Z) - DynaSaur: Large Language Agents Beyond Predefined Actions [108.75187263724838]
Existing LLM agent systems typically select actions from a fixed and predefined set at every step.
We propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner.
Our experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods.
arXiv Detail & Related papers (2024-11-04T02:08:59Z) - LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Integration of Multi Active/Passive Core-Agents [0.0]
We propose a novel LLM-based Agent Unified Modeling Framework (LLM-Agent-UMF)
Our framework distinguishes between the different components of an LLM-based agent, setting LLMs and tools apart from a new element, the core-agent.
We evaluate our framework by applying it to thirteen state-of-the-art agents, thereby demonstrating its alignment with their functionalities.
arXiv Detail & Related papers (2024-09-17T17:54:17Z) - EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms [55.77492625524141]
EvoAgent is a generic method to automatically extend specialized agents to multi-agent systems.
We show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents.
arXiv Detail & Related papers (2024-06-20T11:49:23Z) - LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions [8.55917897789612]
We focus on the cooperative tasks of multiple agents with a common goal and communication among them.
We also consider human-in/on-the-loop scenarios enabled by the language component in the framework.
arXiv Detail & Related papers (2024-05-17T22:10:23Z) - AgentLite: A Lightweight Library for Building and Advancing
Task-Oriented LLM Agent System [91.41155892086252]
We open-source a new AI agent library, AgentLite, which simplifies research investigation into LLM agents.
AgentLite is a task-oriented framework designed to enhance the ability of agents to break down tasks.
We introduce multiple practical applications developed with AgentLite to demonstrate its convenience and flexibility.
arXiv Detail & Related papers (2024-02-23T06:25:20Z) - Recommender AI Agent: Integrating Large Language Models for Interactive
Recommendations [53.76682562935373]
We introduce an efficient framework called textbfInteRecAgent, which employs LLMs as the brain and recommender models as tools.
InteRecAgent achieves satisfying performance as a conversational recommender system, outperforming general-purpose LLMs.
arXiv Detail & Related papers (2023-08-31T07:36:44Z) - MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework [32.95727162682409]
We introduce MetaGPT, an innovative metaprogramming framework incorporating efficient human into multi-agent collaborations.
MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined verification.
On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems.
arXiv Detail & Related papers (2023-08-01T07:49:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.