When Reasoning Meets Its Laws

Junyu Zhang ^∗  Yifan Sun ^∗  Tianang Leng ^∗  Jingyan Shen ^∗ 
Liu Ziyin ^†  Paul Pu Liang ^†  Huan Zhang ^† 
University of Illinois Urbana-Champaign  Massachusetts Institute of Technology
 University of Pennsylvania  New York University  NTT Research
^∗ Equal contribution ^† Equal mentorship

🚀 News

• [2025/11] LoRe was selected as a Best Paper Nomination at the NeurIPS 2025 Workshop on Efficient Reasoning.

🏠 About

Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities.

We present the Laws of Reasoning (LoRe), a unified framework that characterizes intrinsic reasoning patterns in LRMs. LoRe introduces the compute law with the supplementary accuracy law, examined through two properties: monotonicity and compositionality. LoRe-Bench, our proposed benchmark, systematically measures these two tractable properties for LRMs. To address the compositionality gap observed in existing models, we develop an effective finetuning approach that enforces compute-law compositionality.

As a comprehensive study from theoretical hypotheses to empirical validation, we advance a theoretical perspective grounded in human reasoning for improving reasoning in LRMs. We hope LoRe can inspire more potential strategies that guide models toward their optimal paradigms of thinking.

🚧 Code release under construction — stay tuned! 🚧

Model Zoo

Our SFT-Compo models are available on Hugging Face 🤗.

Model	Size	SFT Data	Checkpoint
SFT-Compo	1.5B	deepscaler-14b-min	SFT-Compo-Distill-Qwen-1.5B
SFT-Compo	7B	deepscaler-14b-min	SFT-Compo-Distill-Qwen-7B
SFT-Compo	8B	deepscaler-14b-min	SFT-Compo-Distill-Llama-8B

Contact

If you have any questions related to the code or the paper, feel free to email Junyu Zhang (junyuz6@illinois.edu).

Citation

If you find our work useful in your research, please consider citing LoRe:

@article{LoRe25,
  title={When Reasoning Meets Its Laws},
  author={Zhang, Junyu and Sun, Yifan and Leng, Tianang and Shen, Jingyan and Ziyin, Liu and Liang, Paul Pu and Zhang, Huan},
  journal={arXiv preprint arXiv:2512.17901},
  year={2025}
}