AI RESEARCH
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
arXiv CS.LG
•
ArXi:2411.10109v2 Announce Type: replace-cross Machine learning can predict human behavior well when substantial structured data and well-defined outcomes are available, but these models are typically limited to specific outcomes and cannot readily be applied to new domains. We test whether large language models (LLMs) can a general-purpose approach by building person-specific simulations (i.e., "generative agents") grounded in self-report data.