GAIR-NLP / OctoThinkerLinks
Revisiting Mid-training in the Era of Reinforcement Learning Scaling
☆177Updated 3 months ago
Alternatives and similar repositories for OctoThinker
Users that are interested in OctoThinker are comparing it to the libraries listed below
Sorting:
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆186Updated 4 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆114Updated 5 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 9 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆83Updated 7 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆119Updated last month
- The official repository of the Omni-MATH benchmark.☆88Updated 10 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆178Updated 3 months ago
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆170Updated 3 months ago
- ☆334Updated 2 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆115Updated 10 months ago
- A repo for open research on building large reasoning models☆107Updated last week
- ☆63Updated 4 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆164Updated 7 months ago
- The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]☆91Updated 6 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆112Updated 6 months ago
- ☆99Updated 2 weeks ago
- SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution☆90Updated last month
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆136Updated 6 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆145Updated 4 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆68Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆113Updated 2 months ago
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆93Updated 2 months ago
- ☆73Updated 7 months ago
- The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"☆78Updated 3 weeks ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 5 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆121Updated 6 months ago
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆174Updated 5 months ago
- ☆211Updated 8 months ago
- Resources for the Enigmata Project.☆72Updated 2 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆112Updated 2 months ago