Agentic Services Computing

TL;DR

Agentic Services Computing reframes services as autonomous, goal-driven agents that operate within open, dynamic environments by integrating services computing, multi-agent systems, and LLM-based cognition. The approach centers on a four-phase lifecycle (Design, Deployment, Operation, Evolution) and four research dimensions (perception, autonomous decision-making, multi-agent collaboration, evaluation and trustworthiness), underpinned by the Scale framework and a governance-focused end-to-end pipeline. The paper offers a unified framework, architectural patterns, evaluation and governance mechanisms, and a milestone-driven roadmap toward interoperable, trustworthy agentic ecosystems. Overall, ASC promises proactive, adaptable, human-centered digital services with rigorous accountability and sustainability in real-world deployments.

Abstract

The rise of large language model (LLM)-powered agents is transforming services computing, moving it beyond static, request-driven functions toward dynamic, goal-oriented, and socially embedded multi-agent ecosystems. We propose Agentic Services Computing (ASC), a paradigm that reimagines services as autonomous, adaptive, and collaborative agents capable of perceiving, reasoning, acting, and evolving in open and uncertain environments. We organize ASC around a four-phase lifecycle: Design, Deployment, Operation, and Evolution. It is examined through four interwoven research dimensions: (i) perception and context modeling, (ii) autonomous decision-making, (iii) multi-agent collaboration, and (iv) evaluation with alignment and trustworthiness. Rather than functioning as isolated layers, these dimensions evolve together. Contextual grounding supports robust deployment; autonomous reasoning drives real-time action; collaboration emerges from agent interaction; and trustworthiness is maintained as a lifelong, cross-cutting commitment across all lifecycle stages. In developing this framework, we also survey a broad spectrum of representative works that instantiate these ideas across academia and industry, mapping key advances to each phase and dimension of ASC. By integrating foundational principles of services computing with cutting-edge advances in LLM-based agency, ASC offers a unified and forward-looking foundation for building intelligent, accountable, and human-centered service ecosystems.

Figures (8)

• Figure 1: We define Agentic Services Computing as an emergent paradigm that reimagines services as adaptive, goal-driven participants in a dynamic ecosystem, formed through the convergence of services computing, multi-agent systems, and LLM-based agents.
• Figure 2: The orchestration of core sections in this paper.
• Figure 3: Comparison between agentic and traditional services.
• Figure 4: Research framework of Agentic Services Computing, mapping core research dimensions across the service lifecycle. Each cell highlights key technologies and research topics.
• Figure 5: Key dimensions of perception, context, and environment modeling in agentic services.

Theorems & Definitions (1)

• Definition 1: Agentic Services Computing