MatrAIx: Simulating the World with 8.3 Billion Persona Agents

2026-08-04

AI Summary

This work addresses the limitations of traditional AI evaluation, which relies on costly and inefficient human studies and struggles to capture user diversity and interactive behaviors through offline methods. To overcome these challenges, the authors propose MatrAIx—the first large-scale user evaluation infrastructure capable of simulating billions of fine-grained personas. Built upon a 1,290-dimensional attribute space, MatrAIx constructs the Persona-8B dataset by integrating dependency-graph sampling with curated human profiles and leverages advanced large language models, including Claude Opus 4.8 and GPT 5.5, to power autonomous agents. These agents perform 1,010 cross-domain tasks across four interactive environments: questionnaires, chatbots, websites, and mobile applications. Experiments demonstrate that the system accurately expresses or suppresses predefined behaviors in 91.5% of controlled trials and releases over one million high-quality core personas, effectively capturing individual differences in traits such as price sensitivity and error tolerance.

Abstract

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

Problem

• human evaluation
• scalability
• user diversity
• interactive behavior
• AI system evaluation

Innovation

• simulated-user evaluation
• persona agents
• population-scale simulation
• heterogeneous user modeling
• AI system benchmarking