The Society of HiveMind: Multi-Agent Optimization of Foundation Model Swarms to Unlock the Potential of Collective Intelligence
This work addresses the challenge of scalability and reasoning in AI foundation models for researchers and practitioners, though it appears incremental as it builds on existing multi-agent and swarm intelligence concepts.
The paper tackles the problem of enhancing AI foundation models' reasoning capabilities by developing the Society of HiveMind (SOHM) framework, which orchestrates multi-agent interactions inspired by animal swarms, resulting in significant improvement on logical reasoning tasks but negligible benefit on knowledge-based tasks.
Multi-agent systems address issues of accessibility and scalability of artificial intelligence (AI) foundation models, which are often represented by large language models. We develop a framework - the "Society of HiveMind" (SOHM) - that orchestrates the interaction between multiple AI foundation models, imitating the observed behavior of animal swarms in nature by following modern evolutionary theories. On the one hand, we find that the SOHM provides a negligible benefit on tasks that mainly require real-world knowledge. On the other hand, we remark a significant improvement on tasks that require intensive logical reasoning, indicating that multi-agent systems are capable of increasing the reasoning capabilities of the collective compared to the individual agents. Our findings demonstrate the potential of combining a multitude of diverse AI foundation models to form an artificial swarm intelligence capable of self-improvement through interactions with a given environment.