complex-reasoning / RPGLinks
Official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)
☆63Updated 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☆93Updated 6 months ago
- The official implementation of Self-Exploring Language Models (SELM)☆63Updated last year
- ☆45Updated 6 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆41Updated 2 weeks ago
- ☆50Updated 11 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆168Updated this week
- Official repo of paper LM2☆46Updated 11 months ago
- Defeating the Training-Inference Mismatch via FP16☆172Updated 2 months ago
- ☆79Updated 2 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆173Updated 3 months ago
- ☆33Updated last year
- P1: Mastering Physics Olympiads with Reinforcement Learning☆69Updated 2 weeks ago
- Verlog: A Multi-turn RL framework for LLM agents☆67Updated 2 weeks ago
- ☆123Updated 10 months ago
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆147Updated 3 months ago
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆34Updated 3 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☆102Updated last week
- ☆126Updated this week
- Official Repository of Native Parallel Reasoner☆96Updated 3 weeks ago
- ☆112Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆136Updated 3 weeks ago
- Resa: Transparent Reasoning Models via SAEs☆47Updated 3 months ago
- ☆88Updated 2 months ago
- ☆19Updated 5 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆118Updated this week
- ☆109Updated 4 months ago
- ☆91Updated last year
- Esoteric Language Models☆107Updated last month
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago
- ☆35Updated 7 months ago