arXiv AI July 24, 2026 By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 3

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.

By Matthew Nguyen, Kyle Cox, Austin Meek, Iv\'an Arcuschin

safety

arXiv AI

Jun 11

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

arXiv:2606. 11211v1 Announce Type: cross Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment.

By Prakul Sunil Hiremath, Harshit R. Hiremath

llms

arXiv AI

Jun 12

Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

arXiv:2606. 13603v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly understood.

By Daniel Scalena, Sara Candussio, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti

llms

arXiv AI

Jul 14

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.

By Daeyeop Lee, Hwanjo Yu

llms efficiency benchmarks

arXiv AI

Jun 26

Where Do CoT Training Gains Land in LLM based Agents?

arXiv:2606. 26935v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown that verbalized CoT is not always faithful and may instead reflect post-hoc reasoning, which means the model already knows the answer before reasoning.

By Jingyu Liu, Zhiwen Wang, Yuxin Jing, Huanyu Zhou, Yong Liu

llms agents

arXiv Machine Learning

Jul 14

The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models

arXiv:2603. 16728v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy.

By Robert Welch, Emir Konuk, Kevin Smith

llms multimodal

Related stories

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

Where Do CoT Training Gains Land in LLM based Agents?

The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models