THUDM / T1Links
RL Scaling and Test-Time Scaling (ICML'25)
☆112Updated 11 months ago
Alternatives and similar repositories for T1
Users that are interested in T1 are comparing it to the libraries listed below
Sorting:
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆119Updated 8 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆178Updated 6 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 5 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆48Updated last year
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆147Updated last year
- official implementation of paper "Process Reward Model with Q-value Rankings"☆65Updated 11 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆113Updated 5 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆134Updated 9 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆210Updated last month
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆119Updated last year
- Repo of paper "Free Process Rewards without Process Labels"☆168Updated 10 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆86Updated 9 months ago
- ☆80Updated 10 months ago
- The official repository of the Omni-MATH benchmark.☆91Updated last year
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆70Updated 10 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆129Updated 2 months ago
- ☆70Updated 7 months ago
- ☆213Updated 10 months ago
- [ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLM…☆67Updated last year
- ☆104Updated last year
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆85Updated 7 months ago
- [ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches☆59Updated 10 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆115Updated 5 months ago
- Process Reward Models That Think☆73Updated last month
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆76Updated 7 months ago
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆181Updated 7 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆76Updated 3 months ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAI☆114Updated this week
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆38Updated last year
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆107Updated 10 months ago