Reproducible macroscopic dynamics in a closed-loop human-AI learning system

2026-08-31

AI Summary

研究通过分析大量学习者的行为数据，定义并测试了语义顺序变量，使用四条件机制恢复群体漂移，揭示了人机闭环系统中可重现的宏观动态。

Abstract

Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we define semantic order variables before model fitting and test them in user-disjoint cohorts. The state exhibits reproducible basin-like flow and operationally defined, state-heterogeneous metastable-like kinetics. A construction-matched null distinguishes normalised-memory relaxation from a reproducible excess field. A four-term conditional mechanism recovers population drift (r = 0.946; learner-bootstrap 95% CI, 0.935-0.955). Predictive event-level self-supervised learning recovers the state and learned-plane flow; null-referenced corrections retain directional, partial-amplitude excess-field structure without full calibration. Shuffled-order training reverses learned-plane flow on ordered trajectories; support-alignment randomisation selectively reduces inward transport. Both axes remain linearly accessible without state supervision. Without cross-model fitting, the models share leading population drift (r = 0.866; learner-bootstrap 95% CI, 0.857-0.875) and persistence ordering; residual directions remain model-specific. These results identify an externally anchored leading-order effective field linking empirical dynamics, an interpretable mechanism and neural computation.

Problem

• closed-loop human-AI systems
• high-dimensional behavioural trajectories
• collective dynamics

Innovation

• closed-loop human-AI systems
• semantic order variables
• metastable-like kinetics
• conditional mechanism
• self-supervised learning