THUDM / ReST-MCTSLinks
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
☆670Updated 8 months ago
Alternatives and similar repositories for ReST-MCTS
Users that are interested in ReST-MCTS are comparing it to the libraries listed below
Sorting:
- A series of technical report on Slow Thinking with LLM☆739Updated last month
- ☆549Updated 9 months ago
- ☆341Updated 4 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆325Updated last year
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆383Updated 8 months ago
- ☆948Updated 3 months ago
- ☆962Updated 8 months ago
- A version of verl to support diverse tool use☆570Updated this week
- RewardBench: the first evaluation tool for reward models.☆640Updated 3 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆330Updated this week
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆923Updated 7 months ago
- Large Reasoning Models☆804Updated 10 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆497Updated 11 months ago
- ☆318Updated 4 months ago
- The related works and background techniques about Openai o1☆222Updated 8 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆258Updated last year
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆627Updated 2 weeks ago
- ☆297Updated 4 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 5 months ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆280Updated last year
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆276Updated this week
- [NeurIPS 2025 Spotlight] ReasonFlux Series - ReasonFlux, ReasonFlux-PRM and ReasonFlux-Coder☆492Updated last week
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆818Updated 2 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆319Updated 5 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆136Updated 2 months ago
- ☆352Updated 3 months ago
- Deepseek R1 zero tiny version own reproduce on two A100s.☆71Updated 8 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆356Updated last week
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆246Updated last month
- Paper list for Efficient Reasoning.☆669Updated 2 weeks ago