complex-reasoning / RPGLinks
[ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
☆65Updated last week
Alternatives and similar repositories for RPG
Users that are interested in RPG are comparing it to the libraries listed below
Sorting:
- Reinforcing General Reasoning without Verifiers☆96Updated 7 months ago
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆36Updated 4 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Updated last month
- Official repo of paper LM2☆46Updated 11 months ago
- ☆33Updated last year
- ☆19Updated 6 months ago
- Esoteric Language Models☆110Updated 2 months ago
- ☆134Updated last week
- Defeating the Training-Inference Mismatch via FP16☆181Updated 2 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆119Updated 3 weeks ago
- ☆91Updated last year
- The official implementation of Self-Exploring Language Models (SELM)☆63Updated last year
- Resa: Transparent Reasoning Models via SAEs☆47Updated 4 months ago
- PostTrainBench measures how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆131Updated this week
- P1: Mastering Physics Olympiads with Reinforcement Learning☆73Updated last month
- ☆45Updated 7 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆138Updated last month
- Official Repository of Native Parallel Reasoner☆100Updated 2 weeks ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆177Updated 3 weeks ago
- Code for "Reasoning to Learn from Latent Thoughts"☆124Updated 10 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆67Updated 3 weeks ago
- Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge☆104Updated last week
- ☆123Updated 11 months ago
- ☆110Updated 4 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆175Updated 4 months ago
- [ICLR 2026] Official PyTorch Implementation of RLP: Reinforcement as a Pretraining Objective☆231Updated last week
- ☆50Updated 11 months ago
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆150Updated 4 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆115Updated 9 months ago