zitian-gao / SC-MCTSLinks
Interpretable Contrastive Monte Carlo Tree Search Reasoning
☆48Updated 8 months ago
Alternatives and similar repositories for SC-MCTS
Users that are interested in SC-MCTS are comparing it to the libraries listed below
Sorting:
- RL Scaling and Test-Time Scaling (ICML'25)☆109Updated 6 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆105Updated 2 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆60Updated 5 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆123Updated 10 months ago
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆82Updated 2 months ago
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆147Updated 9 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆125Updated 4 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆139Updated 10 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆103Updated last week
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆76Updated 4 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆160Updated 4 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆61Updated 7 months ago
- ☆48Updated 9 months ago
- Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)☆61Updated 9 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆63Updated 7 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆158Updated last week
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆69Updated 3 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.