Pinned Loading

1. CHATS-lab/verbalized-sampling CHATS-lab/verbalized-sampling Public

   Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. …

   Python 647 78

2. spiral-rl/spiral spiral-rl/spiral Public

   SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

   Python 173 20

3. ChenmienTan/RL2 ChenmienTan/RL2 Public

   Python 1k 103

4. LeonGuertler/TextArena LeonGuertler/TextArena Public

   A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

   Python 334 77

5. axon-rl/gem axon-rl/gem Public

   A Gym for Agentic LLMs

   Python 415 27

6. Cohere-Labs-Community/iterative-data-selection Cohere-Labs-Community/iterative-data-selection Public

   Python 30 6