AI Agents: From Concept to Code to Commerce a Survey Bridging Aamas and LLMS

For decades, autonomous agents and multiagent systems (AAMAS) have developed foundational theories of autonomy and coordination. While large language models (LLMs) have reignited interest in AI agents, connections to established frameworks remain limited. This paper surveys AAMAS theoretical foundations (Concept), their LLM-based implementations (Code), and societal deployment (Commerce), providing an integrated framework for understanding the current trajectory of AI agents. Importantly, the synergistic combination of AAMAS's rigorous theoretical underpinnings and LLMs' unprecedented natural language processing and commonsense reasoning capabilities will overcome the limitations of each, paving the way for real-world applicable AI agents. This survey intends to bridge the groundbreaking practical advances in AI agents achieved by LLM researchers with established AAMAS theories, thereby catalyzing future progress.