Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

TL;DR

This paper introduces Next-Gen CAPTCHAs that leverage the cognitive gap between humans and AI to provide scalable, dynamic, and robust defenses against advanced GUI-enabled agents capable of solving complex logic puzzles.

Contribution

It presents a novel CAPTCHA framework that uses dynamic, reasoning-based tasks to differentiate humans from AI, supported by a scalable data generation pipeline for large-scale evaluation.

Findings

Achieved high pass rates on complex logic puzzles with advanced AI models.

Developed a scalable, unbounded CAPTCHA generation system.

Demonstrated robustness of the cognitive gap approach against modern AI agents.

Abstract

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent advancements in reasoning-heavy models, such as Gemini3-Pro-High and GPT-5.2-Xhigh have effectively collapsed this security barrier, achieving pass rates as high as 90% on complex logic puzzles like "Bingo". In response, we introduce Next-Gen CAPTCHAs, a scalable defense framework designed to secure the next-generation web against the advanced agents. Unlike static datasets, our benchmark is built upon a robust data generation pipeline, allowing for large-scale and easily scalable evaluations, notably, for backend-supported types, our system is capable of generating effectively unbounded CAPTCHA instances. We exploit the persistent human-agent "Cognitive Gap" in interactive perception, memory, decision-making, and action. By engineering dynamic tasks that require adaptive intuition rather than granular planning, we re-establish a robust distinction between biological users and artificial agents, offering a scalable and diverse defense mechanism for the agentic era.