Tag
This article argues that centralized AI models struggle with dynamic, massive problem spaces, proposing swarm intelligence using lightweight agents and stigmergy as an alternative. It covers algorithms like ACO, PSO, and ABC, notes when they fail, and asks about multi-agent frameworks.
AgentPSO is a particle-swarm-inspired framework that evolves multi-agent reasoning skills by treating agents as particles whose states are natural-language skills. It improves performance on reasoning benchmarks without updating the backbone language model parameters.