Related papers: Open CaptchaWorld: A Comprehensive Web-based Platf…
CAPTCHAs are widely deployed as human verification mechanisms and frequently block intelligent agents from completing end-to-end automation in real-world web environments. Solving modern CAPTCHAs requires robust multi-step visual reasoning…
Benefiting from strong and efficient multi-modal alignment strategies, Large Visual Language Models (LVLMs) are able to simulate human visual and reasoning capabilities, such as solving CAPTCHAs. However, existing benchmarks based on visual…
This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We…
Online services rely on CAPTCHAs as a first line of defense against automated abuse, yet recent advances in multi-modal large language models (MLLMs) have eroded the effectiveness of conventional designs that focus on text recognition or 2D…
CAPTCHA, originally designed to distinguish humans from robots, has evolved into a real-world benchmark for assessing the spatial reasoning capabilities of vision-language models. In this work, we first show that step-by-step reasoning is…
As automated attack techniques rapidly advance, CAPTCHAs remain a critical defense mechanism against malicious bots. However, existing CAPTCHA schemes encompass a diverse range of modalities -- from static distorted text and obfuscated…
CAPTCHAs have long been essential tools for protecting applications from automated bots. Initially designed as simple questions to distinguish humans from bots, they have become increasingly complex to keep pace with the proliferation of…
Multimodal Large Language Models (MLLMs) have demonstrated impressive abilities across various tasks, including visual question answering and chart comprehension, yet existing benchmarks for chart-related tasks fall short in capturing the…
With the rapid progress of Multimodal LLMs, evaluating their mathematical reasoning capabilities has become an increasingly important research direction. In particular, visual-textual mathematical reasoning serves as a key indicator of an…
The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present…
Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed…
Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mistakes. Video games offer an ideal testbed with rich visual…
Large Language Models (LLMs) have the potential to enhance Agent-Based Modeling by better representing complex interdependent cybersecurity systems, improving cybersecurity threat modeling and risk management. However, evaluating LLMs in…
Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions and constrained environments, puzzlehunts requires…
Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…
Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promising performance by focusing on visual features or leveraging…
As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations in a lack of external feedback, these agents struggle with…
Large language models (LLMs) have become increasingly pivotal across various domains, especially in handling complex data types. This includes structured data processing, as exemplified by ChartQA and ChatGPT-Ada, and multimodal…
LLM-based agents are increasingly expected to handle real-world assistant tasks, yet existing benchmarks typically evaluate them under isolated sources of difficulty, such as a single environment or fully specified instructions. This leaves…
AI agents with advanced reasoning and tool use capabilities have demonstrated impressive performance in web browsing for deep search. While existing benchmarks such as BrowseComp evaluate these browsing abilities, they primarily focus on…