NineAbyss / S2RLinks
This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"
☆72Updated 8 months ago
Alternatives and similar repositories for S2R
Users that are interested in S2R are comparing it to the libraries listed below
Sorting:
- ☆51Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆142Updated last month
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆73Updated 5 months ago
- A Sober Look at Language Model Reasoning☆92Updated last month
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 5 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆126Updated 8 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆154Updated 5 months ago
- [AAAI 2026] Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆92Updated last month
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆86Updated 9 months ago
- ☆66Updated 6 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆168Updated 9 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆134Updated 9 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆114Updated 4 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆49Updated 6 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆26Updated last year
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆25Updated 4 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆118Updated 7 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆123Updated 8 months ago
- R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning☆66Updated 6 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆86Updated 10 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆70Updated 5 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆63Updated last year
- 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
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆131Updated last month
- ☆346Updated 4 months ago
- ☆51Updated 10 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆61Updated 7 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆65Updated 10 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆50Updated 5 months ago