Skip to content

@PRIME-RL PRIME-RL

Change the repository type filter

All

    Repositories list

    8 repositories

    • P1-VL

      Public
      P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
      1•13•0•0•Updated Feb 11, 2026Feb 11, 2026

    • RL-Compositionality

      Public
      FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
      Python
      •
      Apache License 2.0
      •5•60•2•0•Updated Jan 26, 2026Jan 26, 2026

    • SimpleVLA-RL

      Public
      [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
      rlvlareasoning
      Python
      •
      MIT License
      •83•1.4k•45•1•Updated Jan 6, 2026Jan 6, 2026

    • P1

      Public
      P1: Mastering Physics Olympiads with Reinforcement Learning
      4•74•3•0•Updated Dec 29, 2025Dec 29, 2025

    • TTRL

      Public
      [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
      rlreasoningllm
      Python
      •
      MIT License
      •72•991•16•0•Updated Sep 26, 2025Sep 26, 2025

    • Entropy-Mechanism-of-RL

      Public
      The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.
      rlreasoningllm
      Python
      •15•420•2•0•Updated Jul 11, 2025Jul 11, 2025

    • PRIME

      Public
      Scalable RL solution for advanced reasoning of language models
      rlreasoningllm
      Python
      •
      Apache License 2.0
      •103•1.8k•8•1•Updated Mar 18, 2025Mar 18, 2025

    • ImplicitPRM

      Public
      Repo of paper "Free Process Rewards without Process Labels"
      rlprmtest-time-scaling
      Python
      •
      Apache License 2.0
      •11•168•12•0•Updated Mar 14, 2025Mar 14, 2025