CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs

arXiv:2609.31957 · cs.CV, cs.AI, cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI, cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/X0X0X00/CaptchaArena

Terminology

• Verifier — 24× in this paper · explained in 2 episodes
• Benchmark — 21× in this paper · explained in 2 episodes
• Reinforcement Learning — 16× in this paper · explained in 4 episodes
• Fine-Tuning — 11× in this paper · explained in 5 episodes
• Grounding — 10× in this paper · explained in 3 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• GRPO — 8× in this paper · explained in 6 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Fidelity — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• LoRA Adapters — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild
• Fara-1.5: Scalable Learning Environments for Computer Use Agents
• Evaluating Large Language Models Trained on Code
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA
• HLL: Can Agents Cross Humanity's Last Line of Verification?
• UI-Venus-2 Technical Report
• CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
• Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
• EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
• Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
• CAPTURE: A Benchmark and Evaluation for LVLMs in CAPTCHA Resolving

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models