Autonomous Decision Systems Using Multi-Agent Artificial Intelligence
TL;DR
This paper highlights how agent-based models integrate with decision frameworks, where cooperation, coordination, and competition lead to intelligent behavior in multi-agent contexts, while addressing challenges like scalability, communication overhead, conflict resolution, conflict resolution, and uncertainty.
Abstract
Autonomous decision systems have become essential in modern intelligent computing, driven by advances in AI and distributed computing. This paper studies multi-agent AI (MAAI) systems, focusing on their theoretical foundations, design methods, and performance before 2018. Multi-agent systems enable decentralized, scalable, and adaptive decision-making by distributing intelligence among interacting agents capable of perception, reasoning, and action. The paper highlights how agent-based models integrate with decision frameworks, where cooperation, coordination, and competition lead to intelligent behavior. It reviews approaches such as rule-based systems, utility models, and reinforcement learning in multi-agent contexts, while addressing challenges like scalability, communication overhead, conflict resolution, and uncertainty. It also examines key developments in distributed AI, including contract net protocols, distributed constraint satisfaction, and game-theoretic methods, along with applications in robotics, smart grids, traffic, and defense. Finally, it discusses system evaluation metrics like efficiency, convergence, and fault tolerance, offering a consolidated reference and identifying future research directions.