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

Authors:Minlin Wu (1), Xu Fang (1), Yicheng Zhang (2), Chenyu Zhou (1), Zhiyi Liu (1) ((1) Tianli Qiming AI Research Institute, Sichuan Qiming Daren Technology Co., Ltd., Chengdu, China, (2) Swiss AI Laboratories, Blonay, Switzerland)

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.

Machine Learning (cs.LG); Adaptation and Self-Organizing Systems (nlin.AO)

arXiv:2608.30946 [cs.LG]

(or arXiv:2608.30946v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.30946 arXiv-issued DOI via DataCite (pending registration)