Recent advancements in GUI agents have significantly expanded their ability to interpret natural language commands to manage software interfaces. However, acquiring GUI data remains a significant challenge. Existing methods often involve designing automated agents that browse URLs from the Common Crawl, using webpage HTML to collect screenshots and corresponding annotations, including the names and bounding boxes of UI elements. However, this method is difficult to apply to desktop software or some newly launched websites not included in the Common Crawl. While we expect the model to possess strong generalization capabilities to handle this, it is still crucial for personalized scenarios that require rapid and perfect adaptation to new software or websites. To address this, we propose an automated data collection method with minimal annotation costs, named Auto-Explorer. It incorporates a simple yet effective exploration mechanism that autonomously parses and explores GUI environments, gathering data efficiently. Additionally, to assess the quality of exploration, we have developed the UIXplore benchmark. This benchmark creates environments for explorer agents to discover and save software states. Using the data gathered, we fine-tune a multimodal large language model (MLLM) and establish a GUI element grounding testing set to evaluate the effectiveness of the exploration strategies. Our experiments demonstrate the superior performance of Auto-Explorer, showing that our method can quickly enhance the capabilities of an MLLM in explored software.

Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.

Microsoft has confirmed that its new Windows update is causing the blue screen of death for users attempting to install the software. The company issued a warning Friday, saying that its Windows Server 2025 is experiencing several bugs that cause the program to fail or at least three hours to restart. However, the bugs have caused the blue screen of death but Microsoft has said it's working on a fix that should roll out in the coming month. In the meantime, users should take precautions when downloading Windows Server 2025 by checking if your computer would be at risk. To determine if the update will cause the blue screen of death (BSOD), Microsoft encourages users to use the CTRL SHIFT ESC keys to open Windows Task Manager.

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants.

This paper presents a detailed case study examining the application of Large Language Models (LLMs) in the construction of test cases within the context of software engineering. LLMs, characterized by their advanced natural language processing capabilities, are increasingly garnering attention as tools to automate and enhance various aspects of the software development life cycle. Leveraging a case study methodology, we systematically explore the integration of LLMs in the test case construction process, aiming to shed light on their practical efficacy, challenges encountered, and implications for software quality assurance. The study encompasses the selection of a representative software application, the formulation of test case construction methodologies employing LLMs, and the subsequent evaluation of outcomes. Through a blend of qualitative and quantitative analyses, this study assesses the impact of LLMs on test case comprehensiveness, accuracy, and efficiency. Additionally, delves into challenges such as model interpretability and adaptation to diverse software contexts. The findings from this case study contributes with nuanced insights into the practical utility of LLMs in the domain of test case construction, elucidating their potential benefits and limitations. By addressing real-world scenarios and complexities, this research aims to inform software practitioners and researchers alike about the tangible implications of incorporating LLMs into the software testing landscape, fostering a more comprehensive understanding of their role in optimizing the software development process.

A detailed Description Of the Project Crypto AI ($CAI), an AI-powered NFT (non-fungible token) generator is a software application that uses artificial intelligence and machine learning algorithms to create unique digital assets that can be sold as NFTs. NFTs are blockchain-based tokens that represent ownership of digital assets, such as artwork, music, videos, or any other type of creative content. The AI-powered NFT generator creates original digital assets by analyzing existing content and patterns in the data to generate new, unique creations. For example, an AI-powered NFT generator could analyze a database of images and use machine learning algorithms to create a new image based on the patterns and styles found in the original data. What is the project about?

The data whisperer is the function sitting between the business and the technologists. She, or he, are experts in using data analysis to help organizations better understand their customers and make more informed decisions. They have the ability to interpret large amounts of data and transform it into actionable insights that can inform business decisions. They are also skilled at visualizing data in ways that are easy to understand and interpret. They often work closely with marketing and sales teams to help them identify trends in customer behaviors, develop targeted campaigns, and optimize their overall performance.

RPA-Robotic Process Automation is the most familiar technology in the banking sector. To deliver the best experiences to customers and automate routine tasks, the banking and financial service providers are increasingly deploying RPA applications. Artificial Intelligence (AI) and RPA-enabled virtual banking solutions help banks and financial organizations to optimize the service quality and alter the customer-to-brand interaction ways. In this evolving digital era, RPA-powered mobile apps and enterprise-level software applications are the best assets for banking and financial companies. They help service providers to overcome the challenges that persist in the traditional banking methods, boosting operational efficiency and productivity and remaining on top of the emerging digital world.

Welcome to insideBIGDATA's "Heard on the Street" round-up column! In this regular feature, we highlight thought-leadership commentaries from members of the big data ecosystem. Each edition covers the trends of the day with compelling perspectives that can provide important insights to give you a competitive advantage in the marketplace. We invite submissions with a focus on our favored technology topics areas: big data, data science, machine learning, AI and deep learning. Data is the new oil.

The first two decades of the 21st century have been marked by exponential advances in technology that were once considered elements of a science fiction movie script. Technologies like Artificial intelligence (AI) and Cloud Computing--have stood the test of time and have become mainstream. In this article, we'll look at what these technologies are and how their combination has been a landscape-changing force in the world of modern technology. Simply put, artificial intelligence is the simulation of human intelligence by machines. The integration of artificial intelligence into business allows it to perceive and observe the environment and generate optimal results accordingly--very similar to how people operate, although much faster.