AI RESEARCH

Behavioral Inference at Scale: The Fundamental Asymmetry Between Motivations and Belief Systems

arXiv CS.LG

ArXi:2509.05624v2 Announce Type: replace-cross We establish empirical bounds on behavioral inference through controlled experiments at scale: LLM-based agents assigned one of 36 behavioral profiles (9 belief systems x 4 motivations) generate over 1.5M behavioral sequences across 17,411 games in grid-world environments, providing ground truth unavailable in human behavioral studies. Rather than asking whether inference has limits, we ask how large those limits are, where they concentrate, and why. A fundamental asymmetry emerges in both magnitude and structure.