CaptchaAgent is a structured visual reasoning framework designed to solve modern reasoning CAPTCHAs. It constructs a visual intermediate representation that records entities, attributes, and relations, then refines ambiguous regions and verifies counterfactual consistency before generating actions. The approach yields significant performance gains over baseline browser agents on Open CaptchaWorld and the Oedipus benchmark, highlighting key challenges such as exact counting, geometry, and ordered execution.
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.
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.
arXiv:2512. 02318v4 Announce Type: replace-cross Abstract: This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA.
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...
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?
PerceptRL enhances visual perception in multimodal large language models by employing reinforcement learning that transforms dense image captions into verified QA pairs with rule‑based rewards. It uses a multi‑agent pipeline to link correlated errors, combine unrelated errors, and target high‑error domains, while a specialized multi‑turn inspection process corrects spatial inaccuracies. Across seven benchmarks, PerceptRL improves average accuracy to 71.6%, outperforming both the base model with tools and the leading evaluated VLM by significant margins.
arXiv:2510. 04514v3 Announce Type: replace Abstract: Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts.
arXiv:2606. 15753v1 Announce Type: new Abstract: Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning.
The paper introduces SolveBind, a GUI‑agent framework that tackles verification barriers such as CAPTCHAs by combining hierarchical solving (Perceive, Ground, Solve, Act, Verify) with a runtime supervisor that grounds actions in evidence and manages recovery budgets. Across nine CAPTCHA families and multiple backbone models, SolveBind outperforms baselines by 13.3–34.5 percentage points, achieving the highest success rates on all tested AndroidWorld backbones and improving dynamic verification performance compared to MobileAgent. The study also quantifies the trade‑offs between evidence‑grounded execution control, success rates, latency, and token usage, highlighting the impact of binding and recovery mechanisms on overall efficiency.
arXiv:2512. 11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space.
The paper surveys Multimodal Code Intelligence, focusing on tasks where code is generated, edited, refined, or reasoned about under visually grounded inputs such as screenshots, charts, and videos. It categorizes the field by the role of code—rendered artifact, editable structure, intermediate reasoning trace, or executable tool interface—and organizes benchmarks into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. The authors argue that reliable evaluation must include evidence of semantics and interaction beyond visual fidelity, and propose four verification-centered research directions to advance the field toward evidence-grounded executable systems.
arXiv:2603. 28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations.