Mind wandering and attention

Latest papers

• PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

  Shuhan Xue, Zixin Ding, Yichen Shen, Yinjie Wang, Zhenfei Yin, Yingcheng Wu, Yuxin Chen, Mengdi Wang, Ling Yang · 5 August 2026

  Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for studying this capability because they retain preferences, task histories, tool routines, and learned skills across sessions. Yet whether retained exp…

• Why Meditation Wearables Fail: Reward Misspecification in Closed-Loop EEG and Biofeedback Systems

  Joy Bose · 28 May 2026

  Consumer EEG headbands, HRV biofeedback devices, and closed-loop neurostimulation systems share a fundamental design flaw: they reward measurable proxy signals rather than the outcomes they claim to produce. When a user optimises for calm EEG, HRV coherence, or breathing resonance, their brain learn…

• Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory

  Quanjiang Li, Zhiming Liu, Wei Luo, Tingjin Luo, Chenping Hou · 26 May 2026

  Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly associated with a human-like attention distraction phenomenon, where …

• Why the Unfinished Keeps Returning: Canxianization and the Dynamics of Conscious Priority

  Hengjin Cai, Tianqi Cai · 14 May 2026

  Some conscious contents disappear after access; others return repeatedly, long after their triggering conditions have ceased. We propose Canxianization as the process by which a perturbation becomes closure-resistant self-relevant unfinishedness and thereby acquires recurrent conscious priority. The…

• Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective

  Tokio Kajitsuka, Ukyo Honda, Sho Takase · 13 April 2026

  Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the teacher-student capability mismatch is large. We revisit the capacity gap from a practical perspective by re-examining c…

• Gradual Cognitive Externalization: From Modeling Cognition to Constituting It

  Zhimin Zhao · 8 April 2026

  Developers are publishing AI agent skills that replicate a colleague's communication style, encode a supervisor's mentoring heuristics, or preserve a person's behavioral repertoire beyond biological death. To explain why, we propose Gradual Cognitive Externalization (GCE), a framework arguing that a…

• Gradual Cognitive Externalization: A Framework for Understanding How Ambient Intelligence Externalizes Human Cognition

  Zhimin Zhao · 7 April 2026

  Developers are publishing AI agent skills that replicate a colleague's communication style, encode a supervisor's mentoring heuristics, or preserve a person's behavioral repertoire beyond biological death. To explain why, we propose Gradual Cognitive Externalization (GCE), a framework arguing that h…

• Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models

  Ji Ma, Wei Suo, Peng Wang, Yanning Zhang · 31 March 2026

  Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from severe hallucination problems due to diminished visual attention during the generation process. However, visual attention de…

• Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks

  Yuval Ran-Milo · 13 March 2026

  Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. We prove that computing a simple trigger-conditional behavior necessarily induces a sink in softmax self-attention models. Our results formalize a familiar intuition: normalization over…

• AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM

  Li'an Zhong, Ziqiang He, Jibin Zheng, Jin Li, Z. Jane Wang, Xiangui Kang · 6 March 2026

  Hallucination has been a significant impediment to the development and application of current Large Vision-Language Models (LVLMs). To mitigate hallucinations, one intuitive and effective way is to directly increase attention weights to image tokens during inference. Although this effectively reduce…

• Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education

  Anna Bodonhelyi, Mengdi Wang, Efe Bozkir, Babette B\"uhler, Enkelejda Kasneci · 11 February 2026

  Since the COVID-19 pandemic, online courses have expanded access to education, yet the absence of direct instructor support challenges learners' ability to self-regulate attention and engagement. Mind wandering and disengagement can be detrimental to learning outcomes, making their automated detecti…

• MM-THEBench: Do Reasoning MLLMs Think Reasonably?

  Zhidian Huang, Zijun Yao, Ji Qi, Shangqing Tu, Junxian Ma, Jinxin Liu, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li · 2 February 2026

  Recent advances in multimodal large language models (MLLMs) mark a shift from non-thinking models to post-trained reasoning models capable of solving complex problems through thinking. However, whether such thinking mitigates hallucinations in multimodal perception and reasoning remains unclear. Sel…

• Hallucination Begins Where Saliency Drops

  Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan, Qiyan Zhao, Jiawei Cao, Feilong Tang, Sinan Fan, Yaomin Shen, Chen Shen, Hao Tang · 29 January 2026

  Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguishing hallucinated from factually grounded outputs, as they rely solely on forward-pass attention patterns and neglect gr…

• ExpSeek: Self-Triggered Experience Seeking for Web Agents

  Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li · 14 January 2026

  Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experiences. However, existing methods predominantly inject experience passively as global context before task execution, struggli…

• Output Supervision Can Obfuscate the Chain of Thought

  Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner · 18 November 2025

  OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can …