Comparing Data-Oriented Architectures and Agentic Services Computing for Building Multi-Agent Systems
Overview
Multi-agent systems are designed and architected using styles like microservices or serverless. Recent research proposes extending traditional service-oriented computing to agentic services computing. This extension transforms reusable functional endpoints into goal-oriented autonomous services that can be described, discovered, composed, operated, and governed. Services are interfaces that hide data, creating a data dichotomy: machine learning systems require data exposure for monitoring and adaptation, while services hide it behind interfaces. This dichotomy is one root cause of intellectual debt: systems work in practice, but their designers do not understand their inner workings. This project compares that service style with data-oriented architecture for building multi-agent systems. Data-oriented architecture treats data as a first-class citizen and advocates decentralised, open deployments. DOAgent is a library for building multi-agent systems in which agents coordinate through shared data and can be an starting point for the project.
Theme: Projects on Data-Oriented Multi-Agent Systems
FAQs
- What will I learn in this Project?
You will learn how multi-agent systems are designed with service styles such as microservices or serverless, and how agentic services computing extends service-oriented computing to goal-oriented autonomous services. You will learn the data dichotomy: services hide data behind interfaces, while monitoring and adaptation need that data exposed. You will compare a service-style deployment with a DOAgent session on the same game, and use entropy and modularity as measures of group behaviour.
- What is the objective of the project?
You will compare a service multi-agent system with its Data-Oriented equivalent on information flow. The first goal would be to reproduce an existing multi-agent system implementing both versions. Then, you will compare service runs and data-oriented runs by how closely each record policy recovers the metric curve of its own game. Emergent group behaviour is the object of the study. Entropy and modularity are measures of that behaviour.
- How does this fit into the bigger picture?
This project is part of Data-Oriented Architectures for AI-based Systems. Data-oriented architecture exposes systems’ data as a first-class citizen so that systems can be monitored, reused, and adapted. The broader goal is to address the data dichotomy and mitigate intellectual debt when multi-agent systems are built as services. Information topography is the theory this comparison heads toward. The work also contributes to the Self-Sustaining Software Systems (S4) agenda, where decisions stay readable after the system has run.
Related Group Projects
Data-Oriented Architectures for AI-based Systems
Data Oriented Architecture (DOA) is a software architecture pattern that creates data-driven, loosely coupled, decentralised, and open systems. DOA achieves these goals by exposing systems' data as first class citizen to distributed, stateless, and asynchronous systems’ components. These design decisions enable DOA-based systems to achieve desirable properties such as data availability, reusability, and monitoring, as well as systems adaptability, scalability, and autonomy.
Interfaces
The Interfaces research programme develops interpretable, self-sustaining multi-agent AI systems, treating software as the interface between socio-technical needs and AI capabilities, with validation in healthcare and other high-stakes settings.