Paper | Code

Composition-RL-8B is a large language model fine-tuned for enhanced reasoning using the Composition-RL framework. It was initialized from the Qwen3-8B-Base architecture and trained on the MATH-Composition-199K dataset.

Composition-RL is a data-efficient Reinforcement Learning with Verifiable Rewards (RLVR) approach presented in the paper Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models.

The method addresses the issue of "too-easy" prompts (where pass rates reach 1) that occur as training progresses, which reduces the effective training signal. Composition-RL automatically composes multiple verifiable problems into a single, more challenging compositional prompt, ensuring the model continues to receive informative rewards throughout the reinforcement learning process.

If you find this work helpful for your research, please consider citing: