2025-07-17

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Researchers: Chongli Qin, Jost Tobias Springenberg

Links:

• arXiv paper
• blog post
• github - LLM codebase
• github - Control Suite codebase.
• 32B-reasoning-model.

Contact:

• contact@independentresearch.ai