arXiv AI June 30, 2026 By Yuxi Chen, Haoyu Zhai, Chenkai Wang, Rui Yang, Lingming Zhang, Gang Wang, Huan Zhang

CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training

arXiv:2603. 23559v2 Announce Type: replace-cross Abstract: GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital devices.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision

Sep 24

Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents

The paper introduces Motion Vision CAPTCHA (MVCAP), a new CAPTCHA framework that relies on motion-defined foreground structures to create challenges that are only solvable through temporal analysis of a dynamic background. MVCAP is implemented in three progressive levels—coherent motion, structural motion, and biological motion—and evaluated using the MVCAP-Bench, a browser-based benchmark with 600 live CAPTCHA instances. Human participants achieve 99.6% accuracy, whereas the best GUI agent scores only 16.8%, highlighting a significant human–agent perception gap and demonstrating that dynamic background camouflage is the key difficulty.

By Zeyu Zhang, Dingyi Rong, Zijian Chen, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai

llms agents multimodal benchmarks

arXiv AI

Jun 15

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

arXiv:2512. 02318v4 Announce Type: replace-cross Abstract: This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA.

By Junyu Wang, Changjia Zhu, Yuanbo Zhou, Lingyao Li, Xu He, Mingkui Wei, Junjie Xiong

llms multimodal benchmarks

arXiv AI

Jun 2

HLL: Can Agents Cross Humanity's Last Line of Verification?

arXiv:2606. 02449v1 Announce Type: new Abstract: Multimodal agents are increasingly expected to operate interfaces on behalf of users, raising a central deployment question: can they truly substitute for humans in workflows that services deliberately protect against automation?

By Xinhao Song, Su Su, Sirui Song, Hongliang Wu, Wen Shen, Zhihua Wei, Gongshen Liu, Linfeng Zhang, Dongrui Liu

agents multimodal benchmarks

arXiv AI

Jun 30

GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

arXiv:2606. 29705v1 Announce Type: new Abstract: Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models.

By Sunqi Fan, Lingshan Chen, Runqi Yin, Qingle Liu, Yongming Rao, Meng-Hao Guo, Shi-Min Hu

agents reinforcement-learning

arXiv Computer Vision

Sep 1

Breaking Darknet CAPTCHAs with general purpose LLM

arXiv:2608.28794v1 Announce Type: cross Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs...

By Benjamin Fehrensen, Jens Hubler

llms agents computer-vision safety

arXiv Machine Learning

2d ago

Learning Reliable GUI Agents under Imperfect Priors

arXiv:2609.39547v1 Announce Type: new Abstract: GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GU...

By Bo Han, Qianyi Wang, Shuai Liu, Xiong Zifan, Changqiao Wu, Yuanfa Li, Pengzhi Gao, Wei Liu, Jian Luan, Heng Qu, Yunpeng Song, Zhongmin Cai

llms rag agents multimodal benchmarks

One email a morning, machine-written

Related stories

Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

HLL: Can Agents Cross Humanity's Last Line of Verification?

GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

Breaking Darknet CAPTCHAs with general purpose LLM

Learning Reliable GUI Agents under Imperfect Priors