Rethinking the Trust Region in LLM Reinforcement Learning
☆75Mar 2, 2026Updated 7 months ago
Alternatives and similar repositories for Stable-RL
Users that are interested in Stable-RL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reinforcing General Reasoning without Verifiers☆102Jun 24, 2025Updated last year
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆35Apr 27, 2026Updated 5 months ago
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 5 months ago
- Official Implementation of "Maximum Likelihood Reinforcement Learning (MaxRL)"☆218May 28, 2026Updated 4 months ago
- ☆46Dec 25, 2025Updated 9 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆78Jun 29, 2026Updated 3 months ago
- Knowledge transfer from high-resource to low-resource programming languages for Code LLMs☆17Aug 12, 2025Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆172Mar 2, 2026Updated 7 months ago
- Code for "Variational Reasoning for Language Models"☆61Sep 29, 2025Updated last year
- ☆35Oct 8, 2025Updated last year
- repo for paper https://arxiv.org/abs/2504.13837☆354Jul 27, 2026Updated 2 months ago
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.☆130Apr 7, 2026Updated 6 months ago
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improving☆25Apr 6, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Reinforcement Learning via Self-Distillation (SDPO)☆1,117Jul 1, 2026Updated 3 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆671Jan 29, 2026Updated 8 months ago
- Code for "What really matters in matrix-whitening optimizers?"☆25Oct 31, 2025Updated 11 months ago
- Official implementation of the ΔBelief-RL method.☆31Feb 28, 2026Updated 7 months ago
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Jan 4, 2024Updated 2 years ago
- Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning☆44Jul 2, 2025Updated last year
- Defeating the Training-Inference Mismatch via FP16☆197Nov 14, 2025Updated 10 months ago
- [ICLR2026] DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs☆24Oct 19, 2025Updated 11 months ago
- 🦞 ClawMark: A Living-World Benchmark for Multi-Day, Multimodal Coworker Agents☆123May 28, 2026Updated 4 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”☆77Apr 14, 2026Updated 5 months ago
- ☆33Apr 29, 2026Updated 5 months ago
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆1,011Updated this week
- [CVPR 2026 Findings] V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think☆56Apr 28, 2026Updated 5 months ago
- ☆20Sep 16, 2025Updated last year
- Vocabulary Parallelism☆26Mar 10, 2025Updated last year
- [ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models☆168Jun 8, 2026Updated 4 months ago
- Analyzing LLM Alignment via Token distribution shift☆17Jan 26, 2024Updated 2 years ago
- Target Policy Optimization (JAX)☆31Apr 18, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- The official github repo for "Diffusion Language Models are Super Data Learners".☆228Nov 6, 2025Updated 11 months ago
- NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks☆20May 10, 2022Updated 4 years ago
- Implementation of <Orthogonal Model Merging>☆37Aug 5, 2026Updated 2 months ago
- Official implementation of TBA for async LLM post-training.☆32Nov 5, 2025Updated 11 months ago
- [arXiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matchi…☆46Jun 6, 2026Updated 4 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆15Apr 14, 2025Updated last year