Data Party THU

Nov 4, 2025 · Artificial Intelligence

Why Evolution Strategies Beat Reinforcement Learning for Large‑Model Fine‑Tuning

This article reviews the paper “Evolution Strategies at Scale: LLM Fine‑Tuning Beyond Reinforcement Learning”, explaining how parameter‑space exploration via ES provides more stable, sample‑efficient, and reproducible fine‑tuning for billion‑parameter LLMs such as Qwen‑2.5 and LLaMA‑3, and detailing the algorithmic and engineering innovations that make full‑parameter ES practical.