mukhal / ThinkPRMLinks
Process Reward Models That Think
☆47Updated last month
Alternatives and similar repositories for ThinkPRM
Users that are interested in ThinkPRM are comparing it to the libraries listed below
Sorting:
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆103Updated last week
- ☆47Updated 5 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆109Updated 6 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆76Updated 4 months ago
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆82Updated 2 months ago
- ☆53Updated last month
- official implementation of paper "Process Reward Model with Q-value Rankings"☆60Updated 6 months ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆99Updated last month
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆105Updated 3 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆169Updated 3 weeks ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆161Updated 2 weeks ago
- ☆80Updated 2 weeks ago
- ☆18Updated this week
- ☆126Updated 2 months ago
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆101Updated 2 months ago
- Open-Source LLM Coders with Co-Evolving Reinforcement Learning☆103Updated 2 weeks ago