Agent-as-a-Service based on Agent Network

2025-05-13

AI Summary

Existing Model Context Protocols (MCP) lack native support for agent-level collaboration. Method: We propose the Agent-as-a-Service with Adaptive Networks (AaaS-AN) paradigm, establishing a multi-agent coordination framework grounded in dynamic agent networks and execution graph scheduling. We introduce the RGPS (Role-Goal-Process-Service) modeling standard, design service discovery, registration, and interoperability protocols, and integrate MCP with RPA-style workflow orchestration. Contribution/Results: The framework enables full lifecycle management of agents, supporting dynamic self-organization, scalable interoperability, and networked collaboration. It achieves state-of-the-art performance on mathematical reasoning and code generation benchmarks. We deploy a Multi-Agent System (MAS) comprising over 100 reusable agent services and publicly release the first large-scale, long-horizon multi-agent workflow dataset—containing 10,000 annotated trajectories—to foster reproducible research in agent coordination.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The rise of large model-based AI agents has spurred interest in Multi-Agent Systems (MAS) for their capabilities in decision-making, collaboration, and adaptability. While the Model Context Protocol (MCP) addresses tool invocation and data exchange challenges via a unified protocol, it lacks support for organizing agent-level collaboration. To bridge this gap, we propose Agent-as-a-Service based on Agent Network (AaaS-AN), a service-oriented paradigm grounded in the Role-Goal-Process-Service (RGPS) standard. AaaS-AN unifies the entire agent lifecycle, including construction, integration, interoperability, and networked collaboration, through two core components: (1) a dynamic Agent Network, which models agents and agent groups as vertexes that self-organize within the network based on task and role dependencies; (2) service-oriented agents, incorporating service discovery, registration, and interoperability protocols. These are orchestrated by a Service Scheduler, which leverages an Execution Graph to enable distributed coordination, context tracking, and runtime task management. We validate AaaS-AN on mathematical reasoning and application-level code generation tasks, which outperforms state-of-the-art baselines. Notably, we constructed a MAS based on AaaS-AN containing agent groups, Robotic Process Automation (RPA) workflows, and MCP servers over 100 agent services. We also release a dataset containing 10,000 long-horizon multi-agent workflows to facilitate future research on long-chain collaboration in MAS.

Problem

• Lack of agent-level collaboration support in MCP protocol
• Need for unified agent lifecycle management in MAS
• Challenges in distributed coordination and task management

Innovation

• Agent-as-a-Service based on Agent Network
• Dynamic Agent Network for self-organizing collaboration
• Service-oriented agents with discovery and interoperability