Contemporary Agent Technology: LLM-Driven Advancements vs Classic Multi-Agent Systems
This is an incremental review paper that synthesizes existing knowledge for researchers in AI and multi-agent systems.
The paper analyzes contemporary agent technology by comparing LLM-driven advancements with classic Multi-Agent Systems, focusing on models, approaches, and characteristics, and identifies key challenges and future directions in the field.
This contribution provides our comprehensive reflection on the contemporary agent technology, with a particular focus on the advancements driven by Large Language Models (LLM) vs classic Multi-Agent Systems (MAS). It delves into the models, approaches, and characteristics that define these new systems. The paper emphasizes the critical analysis of how the recent developments relate to the foundational MAS, as articulated in the core academic literature. Finally, it identifies key challenges and promising future directions in this rapidly evolving domain.