This model is the Chain-of-Thought (CoT) efficient version of
Qwen3-1.7B, developed as part of the research presented in the paper "
The Art of Efficient Reasoning: Data, Reward, and Optimization".
Art-Qwen3-1.7B is optimized for efficient reasoning, aiming to produce short yet accurate thinking trajectories. It was trained using Reinforcement Learning (RL) with specialized reward shaping on the
DeepScaleR-Easy dataset. The training follows a two-stage paradigm involving length adaptation and reasoning refinement to maintain high accuracy while reducing computational overhead.
1@inproceedings{wu2026art,
2 title={The Art of Efficient Reasoning: Data, Reward, and Optimization},
3 author={Taiqiang Wu and Zenan Xu and Bo Zhou and Ngai Wong},
4 year={2026},
5 url={https://arxiv.org/pdf/2602.20945}
6}
