Qwen3-0.6B-Art/README.md

base_model, datasets, language, license, pipeline_tag, library_name

base_model	datasets	language	license	pipeline_tag	library_name
Qwen/Qwen3-0.6B	taki555/DeepScaleR-Easy	en	apache-2.0	text-generation	transformers

Qwen3-0.6B-Art

This is the Chain-of-Thought (CoT) efficient version of the Qwen3-0.6B model, trained on the DeepScaleR-Easy dataset.

This model was introduced in the paper The Art of Efficient Reasoning: Data, Reward, and Optimization. Check the Project Page for more details.

Model Description

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning but also suffer from heavy computational overhead. Efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL).

This model follows a two-stage training paradigm: length adaptation and reasoning refinement. It is optimized to maintain a sufficient density of positive reward signals while avoiding the "short-is-correct" trap, demonstrating robust and generalized efficient reasoning capabilities.

Citation

@inproceedings{wu2026art,
  title={The Art of Efficient Reasoning: Data, Reward, and Optimization},
  author={Taiqiang Wu and Zenan Xu and Bo Zhou and Ngai Wong},
  year={2026},
  url={https://arxiv.org/pdf/2602.20945}
}