Research2026-04-23
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
Source: Arxiv CS.AI
arXiv:2411.10109v2 Announce Type: replace Abstract: 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...
arxivpapersagents