ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. ITBench includes an initial set of 94 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 13.8% of SRE scenarios, 25.2% of CISO scenarios, and 0% of FinOps scenarios. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast.

Catalyzing Social Interactions in Mixed Reality using ML Recommendation Systems

We create an innovative mixed reality-first social recommendation model, utilizing features uniquely collected through mixed reality (MR) systems to promote social interaction, such as gaze recognition, proximity, noise level, congestion level, and conversational intensity. We further extend these models to include right-time features to deliver timely notifications. We measure performance metrics across various models by creating a new intersection of user features, MR features, and right-time features. We create four model types trained on different combinations of the feature classes, where we compare the baseline model trained on the class of user features against the models trained on MR features, right-time features, and a combination of all of the feature classes. Due to limitations in data collection and cost, we observe performance degradation in the right-time, mixed reality, and combination models. Despite these challenges, we introduce optimizations to improve accuracy across all models by over 14 percentage points, where the best performing model achieved 24% greater accuracy.