AI RESEARCH
Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training
arXiv CS.LG
•
ArXi:2604.01499v1 Announce Type: new Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space. We compare ES and Group Relative Policy Optimization (GRPO) across four tasks in both single-task and sequential continual-learning settings. ES matches or exceeds GRPO in single-task accuracy and remains competitive sequentially when its iteration budget is controlled.