Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over different time scales rather than align with fixed observation--action steps. To model such interactions, we propose \emph{Engagement Process} (EP), an interaction formalism that inherits the decision-theoretic structure of POMDPs while making time explicit in the action--observation interface. EP represents actions and observations as decoupled event streams along time, rather than updates paired at fixed decision steps. This interface captures single-agent timing issues such as deliberation latency, delayed feedback, and persistent actions, while supporting richer agent-side organization, multi-rate coordination, and compositional interaction among subsystems. Across toy, LLM-agent, and learning experiments, EP exposes temporal behaviors hidden by step-based interfaces and enables policies to adapt under explicit time costs.
@article{arxiv.2605.11484,
title = {Engagement Process: Rethinking the Temporal Interface of Action and Observation},
author = {Jialian Li and Yuchen Cao and Junhong Liu and Weiran Guo and Xutao Wang and Jiaming Song and Jiahao Zhang and Jie Chen},
journal= {arXiv preprint arXiv:2605.11484},
year = {2026}
}