ResearchTrend.AI
83
1
v1v2 (latest)

(How) Do reasoning models reason?

S. Kambhampati
Kaya Stechly
Karthik Valmeekam
ArXiv (abs)PDFHTML
Main:8 Pages
4 Figures
Bibliography:4 Pages
Abstract

We will provide a broad unifying perspective on the recent breed of Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek R1, including their promise, sources of power, misconceptions and limitations.

View on arXiv
@article{kambhampati2025_2504.09762,
  title={ Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces! },
  author={ Subbarao Kambhampati and Kaya Stechly and Karthik Valmeekam and Lucas Saldyt and Siddhant Bhambri and Vardhan Palod and Atharva Gundawar and Soumya Rani Samineni and Durgesh Kalwar and Upasana Biswas },
  journal={arXiv preprint arXiv:2504.09762},
  year={ 2025 }
}
Comments on this paper