The paper introduces RADAR, a method that models large reasoning models (LRMs) as four states and uses dynamic attention responses to detect uncontrolled reasoning in real time. RADAR identifies abnormal attention patterns that precede repetitive loops, and the authors demonstrate that realigning these patterns reduces looping while maintaining performance. The study offers a mechanistic explanation of how benign reasoning can degenerate into harmful behavior and provides actionable guidance for runtime interventions.
By Yuanhe Zhang, Ziwei Wang, Jie Ren, Haoran Gao, Zhenhong Zhou, Fanyu Meng, Cong Wu, Li Sun, Sen Su
arXiv:2606. 02835v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assumption that longer reasoning is consistently beneficial remains under-examined.
By Simone Caldarella, Davide Talon, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini
The paper investigates why large reasoning models (LRMs) often continue to think even when prompted to stop, a phenomenon called "Still-thinking". By examining confidence at the thinking-termination boundary, internal attention divergences, and attention allocation across prompt segments, the authors find that high perplexity and greater attention to the original question correlate with continued thinking. They propose an attention‑intervention method that suppresses explicit reasoning, which reduces inefficiency but also lowers accuracy, underscoring a trade‑off between instruction compliance, inference speed, and correctness.
By Rongzhi Zhu, Yi Liu, Jiancheng Wang, Xiangyu Liu, Zequn Sun, Yiwei Wang, Yu Deng, Zijian Zhou, Wei Hu
arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.
By Sheldon Yu, Tong Yu, Xunyi Jiang, Rohan Surana, Gagan Mundada, Sungchul Kim, Lina Yao, Julian McAuley, Junda Wu
arXiv:2509.24711v4 Announce Type: replace
Abstract: Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's ope...
By Qingjie Zhang, Yujia Fu, Yang Wang, Liu Yan, Tao Wei, Ke Xu, Minlie Huang, Han Qiu
arXiv:2510. 11713v4 Announce Type: replace-cross Abstract: Real-world applications of Large Reasoning Models (LRMs) often require reasoning about changing prompts or environments.
By Tsung-Han Wu, Mihran Miroyan, David M. Chan, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez
arXiv:2604. 01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks.
By Gleb Rodionov, Roman Garipov, George Yakushev
arXiv:2608. 15065v1 Announce Type: new Abstract: Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deployment.
By Chanhee Park, Sungbin Han, Jeongho Yoon, Seongtae Hong, Heuiseok Lim
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:2606. 11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it.
By Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke, Martin McKee
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
By Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan
The paper argues that large language models need adaptive reasoning rather than fixed reasoning budgets. It shows that over‑reasoning leads to high computational cost without accuracy gains, while under‑reasoning results in incorrect or incomplete solutions. The authors evaluate these failure modes on MATH‑500 and the GAIA benchmark, highlighting the need for dynamic reasoning allocation in agentic AI systems.
By Md Jueal Mia, M. Hadi Amini