# AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis arXiv: https://arxiv.org/abs/2507.21105 ยท HTML: https://mlsanity.com/paper/2507.21105/ ## Key facts - Cited by 13 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 19 of its 38 references that are in the map. - First posted on arXiv 8 Jul 2025. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 19 of 19) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023) - [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023) - [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024) - [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024) - [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025) - [A Survey of AI Agent Protocols](https://mlsanity.com/paper/2504.16736/) (2025) - [Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://mlsanity.com/paper/2402.09205/) (2024) - [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024) - [VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft](https://mlsanity.com/paper/2406.05720/) (2024) - [AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes](https://mlsanity.com/paper/2506.14728/) (2025) - [MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System](https://mlsanity.com/paper/2504.12757/) (2025) - [QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction](https://mlsanity.com/paper/2403.11886/) (2024) - [FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models](https://mlsanity.com/paper/2502.17924/) (2025) - [CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System](https://mlsanity.com/paper/2505.04254/) (2025) - [Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review](https://mlsanity.com/paper/2506.05364/) (2025) - [A Study on the MCP x A2A Framework for Enhancing Interoperability of LLM-based Autonomous Agents](https://mlsanity.com/paper/2506.01804/) (2025) - [InfoTech Assistant: A Multimodal Conversational Agent for InfoTechnology Web Portal Queries](https://mlsanity.com/paper/2412.16412/) (2024) ## Built on by (most cited first, 13 of 13) - [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026) - [The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption](https://mlsanity.com/paper/2601.13671/) (2026) - [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025) - [MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation](https://mlsanity.com/paper/2604.16175/) (2026) - [Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives](https://mlsanity.com/paper/2604.06091/) (2026) - [GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing](https://mlsanity.com/paper/2605.02489/) (2026) - [CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers](https://mlsanity.com/paper/2603.00123/) (2026) - [Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension](https://mlsanity.com/paper/2604.12213/) (2026) - [tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration](https://mlsanity.com/paper/2606.14445/) (2026) - [A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based Systems](https://mlsanity.com/paper/2607.23884/) (2026) - [PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs](https://mlsanity.com/paper/2608.17289/) (2026) - [Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection](https://mlsanity.com/paper/2609.03416/) (2026) - [BirdsongChat: A Hybrid Multi-Agent Framework for Multimodal Embodied Behavior Simulation](https://mlsanity.com/paper/2609.20887/) (2026) ## Abstract (arXiv) The rise of Multi-Agent Systems (MAS) in Artificial Intelligence (AI), especially integrated with Large Language Models (LLMs), has greatly facilitated the resolution of complex tasks. However, current systems are still facing challenges of inter-agent communication, coordination, and interaction with heterogeneous tools and resources. Most recently, the Model Context Protocol (MCP) by Anthropic and Agent-to-Agent (A2A) communication protocol by Google have been introduced, and to the best of our knowledge, very few applications exist where both protocols are employed within a single MAS framework. We present a pilot study of AgentMaster, a novel modular multi-protocol MAS framework with self-implemented A2A and MCP, enabling dynamic coordination, flexible communication, and rapid development with faster iteration. Through a unified conversational interface, the system supports natural language interaction without prior technical expertise and responds to multimodal queries for tasks including information retrieval, question answering, and image analysis. The experiments are validated through both human evaluation and quantitative metrics, including BERTScore F1 (96.3%) and LLM-as-a-Judge G-Eval (87.1%). These results demonstrate robust automated inter-agent coordination, query decomposition, task allocation, dynamic routing, and domain-specific relevant responses. Overall, our proposed framework contributes to the potential capabilities of domain-specific, cooperative, and scalable conversational AI powered by MAS.