---
base_model:
- Qwen/Qwen3-4B-Thinking-2507
datasets:
- taki555/DeepScaleR-Easy
language:
- en
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
---

# Art-Qwen3-4B-Thinking-2507

This is the CoT efficient version of the [Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) model, presented in the paper [The Art of Efficient Reasoning: Data, Reward, and Optimization](https://huggingface.co/papers/2602.20945).

The model was trained on the [DeepScaleR-Easy](https://huggingface.co/datasets/taki555/DeepScaleR-Easy) dataset to incentivize short yet accurate thinking trajectories.

## Model Description
Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. This model addresses efficient reasoning by using a two-stage training paradigm: length adaptation and reasoning refinement. Through reward shaping with Reinforcement Learning (RL), the model is optimized to maintain high performance across a wide spectrum of token budgets while avoiding the "short-is-correct" trap.

For more details, please visit the [Project Page](https://wutaiqiang.github.io/project/Art).

## Citation

```bibtex
@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}
}
```