AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis
This addresses the problem of building more efficient and scalable conversational AI systems for users without technical expertise, though it appears incremental as it combines existing protocols in a new framework.
The authors tackled the challenge of inter-agent communication and coordination in multi-agent systems by developing AgentMaster, a novel framework that integrates both A2A and MCP protocols, achieving high performance with BERTScore F1 of 96.3% and LLM-as-a-Judge G-Eval of 87.1% in multimodal information retrieval and analysis tasks.
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.