首页 > AI前沿 > PsyWorld: Profile-Conditioned World Modeling for Human Behavior Prediction

PsyWorld: Profile-Conditioned World Modeling for Human Behavior Prediction

arXiv机器学习 2026-11-19 00:54 10 阅读 查看原文

研究背景

Understanding how stable psychometric traits and time-varying states jointly inform behavior is an important problem in computational behavioral science. Existing personalized agents commonly condition actions directly on a static profile, leaving realized state transitions unused as an explicit source of supervision.

方法框架

We introduce a profile-conditioned state world model that uses observed environment--behavior state transitions to learn transition-informed representations for behavioral prediction. During training, a posterior encoder quantizes realized transitions, while a prior predicts the resulting codes from the psychometric profile and pre-transition context. The prior code and predicted next state then condition macro-level behavior and simulator-grounded execution. Thus, the world model provides structured transition supervision instead of treating personality as a direct action descriptor.

实验评估

We evaluate the framework in VEET, a controlled behavioral simulator with human trajectories, and in AgentSociety as a structurally different synthetic environment. A participant-disjoint split of 240 training, 25 validation, and 48 test participants evaluates generalization to unseen people. On VEET, the model reaches 0.904 Top-1 accuracy (95\% CI: [0.895, 0.913]) and 0.0033 Macro KL.

消融分析与结论

Ablations associate continuous next-state modeling with most of the Top-1 gain, while discrete codes and prior alignment mainly improve Top-3 and distributional alignment. These results establish transition-informed world-model supervision as useful for subject-generalized behavior prediction, without implying causal psychological mechanisms or calibrated long-horizon state dynamics.