PRIME-RL / RL-CompositionalityLinks
FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
☆46Updated last month
Alternatives and similar repositories for RL-Compositionality
Users that are interested in RL-Compositionality are comparing it to the libraries listed below
Sorting:
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 5 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆124Updated 9 months ago
- A repo for open research on building large reasoning models☆125Updated this week
- AnchorAttention: Improved attention for LLMs long-context training☆213Updated 11 months ago
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆187Updated 5 months ago
- Process Reward Models That Think☆67Updated last month
- ☆87Updated 2 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆211Updated last month
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆180Updated 5 months ago
- The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆15Updated 3 months ago
- A Sober Look at Language Model Reasoning☆92Updated last month
- ☆105Updated 2 weeks ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆118Updated 7 months ago
- ☆54Updated 2 months ago
- Reinforcing General Reasoning without Verifiers☆93Updated 6 months ago
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆105Updated 7 months ago
- Code for "Variational Reasoning for Language Models"☆53Updated 3 months ago
- ☆68Updated 6 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆67Updated 8 months ago
- ☆106Updated 2 weeks ago
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆110Updated 4 months ago
- ☆108Updated 3 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆86Updated 9 months ago
- ☆108Updated 7 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆112Updated 11 months ago
- Long Context Extension and Generalization in LLMs☆62Updated last year
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆55Updated 3 months ago
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆89Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆136Updated last week
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆126Updated 8 months ago