Agent-as-a-Service based on Agent Network
Yuhan Zhu, Haojie Liu, Jian Wang, Bing Li, Zikang Yin, Yefei Liao
TL;DR
This work tackles the challenge of end-to-end automation and scalable collaboration in large-scale MAS by introducing AaaS-AN, a RGPS-driven service-oriented framework. It unifies agent construction, integration, interoperability, and networked collaboration with two core components—the dynamic Agent Network and service-oriented agents—coordinated by a Service Scheduler and Execution Graph. Through rigorous experiments in mathematical reasoning and application-level code generation, AaaS-AN outperforms state-of-the-art baselines and is demonstrated at scale with over 100 agent services and MCP servers, accompanied by a 10,000-flow long-horizon dataset. The proposed architecture enhances interoperability, modularity, and long-chain collaboration in MAS, with practical implications for RPA workflows and tool integration.
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.