Decoded
Feed

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

arXiv:2608.04205AI4 aug 20261 min read2 citationsHN ×6PDF

A pool of 8.3 billion simulated people for testing apps and chatbots before real users see them.

91.5%

Trials where agents followed persona

Simulated users must act like their assigned traits to be useful.

How it works

  1. Real users are costly

    Human studies take weeks. Offline benchmarks check task success but ignore how different people use and judge a product.

  2. Simulate diverse users

    Sample personas from 1,290 linked attributes, pair each with an LLM, and run them through surveys, chatbots, websites and apps.

  3. Personas mostly hold

    Across 18,189 trials, agents kept assigned behaviors in 366 of 400 controlled tests; native apps were the weakest.

queryassigninteractartifactsfindingsPersona8B poolCohortsamplingLLM personaagentsFourenvironmentsTaskverifierSubgroupreportsqueryassigninteractartifactsfindingsPersona8B poolCohortsamplingLLM personaagentsFourenvironmentsTaskverifierSubgroupreports
From the paper