OraCore · Topic ·research

PreRL: Training LLMs in pre-train space

PreRL shifts reinforcement learning from P(y|x) to P(y), using reward-driven updates in pre-train space to improve reasoning and exploration.

1 articles in this thread ·Last updated 19h ago·First seen Jul 5, 2026

Timeline

  1. PreRL: Training LLMs in pre-train space seed

    PreRL shifts reinforcement learning from P(y|x) to P(y), using reward-driven updates in pre-train space to improve reasoning and exploration.