arXiv:2512.00729v2 Announce Type: replace
Abstract: Motivated by the observed human-like behaviours in Large Reasoning Models (LRMs), this paper introduces a comprehensive taxonomy to characterise at...
By Yuxiang Chen, Zuohan Wu, Ziwei Wang, Xiangning Yu, Xujia Li, Linyi Yang, Mengyue Yang, Jun Wang, Lei Chen
The paper investigates a training‑free early‑exit technique that inserts an end‑of‑think (EoT) token to terminate chain‑of‑thought (CoT) reasoning in large reasoning models. It finds that the injected EoT often fails to cleanly switch the model from reasoning to answering, leading to continued reasoning‑like generation—termed spurious CoT termination—whose length scales with the amount of reasoning saved. By increasing attention to the EoT token through Exit‑token Attention Biasing (EAB), the authors reduce spurious termination and shorten the answering phase across multiple models and benchmarks.
By Seunghee Koh, Sungjae Choi, Minchan Kwon, Sunghyun Baek, Junmo Kim
arXiv:2502.09192v3 Announce Type: replace
Abstract: Anthropomorphism, or the attribution of human traits to technology, is an automatic and unconscious response that occurs even in those with advance...
By Lujain Ibrahim, Myra Cheng
arXiv:2504. 12329v2 Announce Type: replace-cross Abstract: Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs.
By Wang Yang, Xiang Yue, Vipin Chaudhary, Xiaotian Han
arXiv:2601. 18383v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer.
By Zhenyuan Guo, Tong Chen, Wenlong Meng, Chen Gong, Xin Yu, Chengkun Wei, Wenzhi Chen
The paper investigates how large language models (LLMs) organize reasoning operations—such as problem formulation, goal decomposition, and deduction—within their hidden representation spaces. It shows that these operations are separable in held‑out representations, with peak separability in middle layers, and that token‑wise alignment of operations becomes more distributed across spans as layers deepen. Attention‑masking experiments reveal that representations aligned to operations at chunk onsets depend on prior reasoning context, indicating a geometric correspondence between linguistic reasoning expressions and internal model structure.
By Seogyeong Jeong, Jaehui Hwang, Dongyoon Han, Geonmo Gu, Alice Oh, Taekyung Kim