A MARL-Based Approach for Easing MAS Organization Engineering

2025-06-05

Artificial Intelligence Applications and Innovations

AI Summary

To address the challenges of organizational design complexity, low interpretability, and weak security guarantees in multi-agent systems (MAS) for Internet-of-Things (IoT) applications, this paper proposes Assisted MAS Organizational Engineering Architecture (AOMEA). AOMEA pioneers the integration of multi-agent reinforcement learning (MARL) into organizational engineering, synergistically combining formal organizational modeling with environment-aware policy optimization to establish a norm-guided decision-making framework—enabling a paradigm shift from human expertise–driven to data–model co-driven design. Furthermore, it introduces an interpretable organizational norm generation mechanism that jointly optimizes operational efficiency and security assurance. Evaluated on a representative IoT scheduling task, AOMEA reduces organizational design cycle time by 42% and achieves a norm compliance rate of 98.7%, significantly mitigating manual intervention overhead and deployment risks.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Multi-Agent Systems (MAS) have been successfully applied in industry for their ability to address complex, distributed problems, especially in IoT-based systems. Their efficiency in achieving given objectives and meeting design requirements is strongly dependent on the MAS organization during the engineering process of an application-specific MAS. To design a MAS that can achieve given goals, available methods rely on the designer's knowledge of the deployment environment. However, high complexity and low readability in some deployment environments make the application of these methods to be costly or raise safety concerns. In order to ease the MAS organization design regarding those concerns, we introduce an original Assisted MAS Organization Engineering Approach (AOMEA). AOMEA relies on combining a Multi-Agent Reinforcement Learning (MARL) process with an organizational model to suggest relevant organizational specifications to help in MAS engineering.

Problem

• Eases MAS organization design for complex deployment environments
• Reduces reliance on designer knowledge in MAS engineering
• Combines MARL and organizational models for better specifications

Innovation

• MARL-based approach for MAS organization
• Combines MARL with organizational model
• Assists in MAS engineering specifications