InternLM / OREALLinks
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
☆192Updated 10 months ago
Alternatives and similar repositories for OREAL
Users that are interested in OREAL are comparing it to the libraries listed below
Sorting:
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆164Updated 4 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆143Updated 2 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆147Updated 9 months ago
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆154Updated 3 weeks ago
- ☆214Updated 11 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆260Updated 8 months ago
- ☆328Updated 8 months ago
- ☆332Updated 8 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆351Updated 3 weeks ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆155Updated last year
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆249Updated 9 months ago
- ☆352Updated 6 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆226Updated 5 months ago
- [AAAI 2026] Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆95Updated 2 months ago
- Towards a Unified View of Large Language Model Post-Training☆200Updated 4 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆116Updated 5 months ago
- ☆87Updated 5 months ago
- ☆68Updated last year
- A set of examples based on verl for end-to-end RL training recipes.☆152Updated this week
- Extrapolating RLVR to General Domains without Verifiers☆196Updated 5 months ago
- ☆222Updated last month
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆406Updated 4 months ago
- ☆209Updated 3 months ago
- Deepseek R1 zero tiny version own reproduce on two A100s.☆83Updated last year
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆153Updated 3 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆168Updated 10 months ago
- A Comprehensive Survey on Long Context Language Modeling☆222Updated 2 months ago
- Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay☆148Updated 8 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆172Updated 3 months ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆283Updated 11 months ago