The paper introduces VERITAS, a method that verbalises a language model’s internal computation during chain‑of‑thought (CoT) generation by projecting layer‑wise Jacobians to produce a token‑by‑token account of reasoning evolution. By training a classifier on these verbalised features, VERITAS detects where and how reasoning diverges toward unfaithfulness, achieving a 28.4% balanced‑accuracy gain over LLM‑as‑Judge and a 16.0% improvement over activation probing across four datasets. The approach demonstrates generalisability to different datasets and model architectures, offering a richer, more interpretable lens on CoT faithfulness that moves beyond detection toward mechanistic insight.
By Yujing Wang, Yulan He, Wenya Wang, Hanqi Yan
arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?
By Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang
arXiv:2607. 20500v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer.
By Sizhe Tang, Guangyu Jiang, Yu Li, Rongqian Chen, Ioannis G. Kevrekidis, Tian Lan
arXiv:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.
By Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov, Pavel Vasiliev, Aleksandr Beznosikov
arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.
By Jinu Lee, Shivam Agarwal, Amruta Parulekar, Siddarth Madala, Dilek Hakkani-Tur, Julia Hockenmaier
arXiv:2606. 07410v1 Announce Type: cross Abstract: The emergence of "Aha moments" in large language models, particularly DeepSeek-R1-0120, has raised the question of whether these systems genuinely reason or merely imitate the appearance of reasoning.
By Yuxiang Chen, Jun Wang
arXiv:2603. 05290v2 Announce Type: replace Abstract: Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood.
By Tianxi Gao, Yufan Cai, Yusi Yuan, Jin Song Dong
arXiv:2509.14093v3 Announce Type: replace-cross
Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with hig...
By Kerui Huang, Shuhan Liu, Xing Hu, Tongtong Xu, Lingfeng Bao, Xin Xia
arXiv:2604. 04902v2 Announce Type: replace Abstract: Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel.
By Connor Dilgren, Sarah Wiegreffe
arXiv:2605. 19723v2 Announce Type: replace-cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems.
By Husnain Amjad, Raja Khurram Shahzad, Aamir Shahzad, Mehwish Fatima
arXiv:2607. 04096v1 Announce Type: new Abstract: Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reasoning traces in the language model's context window.
By Vishvesh Bhat, Jay Vaghasiya, Emmanuel Anaya Gonzalez
The paper investigates how monitoring the internal representations of Large Reasoning Models (LRMs) during their Chain-of-Thought (CoT) reasoning can predict future behavior. By evaluating a probe at each generated token, the authors construct probe trajectories that capture the continuous evolution of a concept’s probability, and extract signal‑processing features to characterize volatility, trend, and steady‑state behavior. These trajectory features improve predictive performance over static probes, adding an average of 21.7 AUROC points, and the study demonstrates that template‑based training data and pooling operations are essential for effective monitoring across multiple reasoning models and datasets.
By Maciej Chrabaszcz, Aleksander Szymczyk, Marcin Sendera, Tomasz Trzcinski, Sebastian Cygert