arXiv · 2026 · Preprint

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close

Date: 2026-04-02
Citations: 5
arXiv: 2604.01499 ↗

Cite

@misc{hoy2026matching,
  title = {Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training},
  author = {William Hoy and BinXu Wang and Xu Pan},
  year = {2026},
  eprint = {2604.01499},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.01499},
}