Publications

* denotes equal contribution · † denotes corresponding authors / equal advising

arXiv2026

[4] Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Chanuk Lee, Minki Kang, Sangwoo Park, Woongyeong Yeo, Jinheon Baek†, Sung Ju Hwang†

@misc{lee2026knowingthinkingenoughteaching,
  title={Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge},
  author={Chanuk Lee and Minki Kang and Sangwoo Park and Woongyeong Yeo and Jinheon Baek and Sung Ju Hwang},
  year={2026},
  eprint={2609.34327},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2609.34327}
}

arXiv2026

[3] Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Woongyeong Yeo, Minki Kang, Chanuk Lee, Sangwoo Park, Jinheon Baek†, Sung Ju Hwang†

Paper Code

@misc{yeo2026surprisingsuccessrepeatedfailure,
  title={Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning},
  author={Woongyeong Yeo and Minki Kang and Chanuk Lee and Sangwoo Park and Jinheon Baek and Sung Ju Hwang},
  year={2026},
  eprint={2609.33781},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2609.33781}
}

MATH-AI@NeurIPS2026

[2] Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Chanuk Lee*, Sangwoo Park*, Minki Kang, Sung Ju Hwang

Paper Code

@article{lee2026nudging,
  title={Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR},
  author={Lee, Chanuk and Park, Sangwoo and Kang, Minki and Hwang, Sung Ju},
  journal={arXiv preprint arXiv:2605.15726},
  year={2026}
}

ICML2026

[1] SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

Chanuk Lee, Minki Kang, Sung Ju Hwang

Paper Code

@article{lee2026sage,
  title={SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs},
  author={Lee, Chanuk and Kang, Minki and Hwang, Sung Ju},
  journal={arXiv preprint arXiv:2605.18864},
  year={2026}
}