Phase 16: Multi-Agent & Swarms
AI From Scratch/Lesson 19/~75 minutes

Swarm Optimization for LLMs (PSO, ACO)

Bio-inspired optimization is making an LLM comeback. LMPSO (arXiv:2504.09247) uses PSO where each particle's velocity is a prompt and the LLM generates the next candidate; works well on structured-sequence outputs (math expressions, progra...

Learn + BuildPython (stdlib)
Loading lesson page...