提出显式时间接口的交互框架，让智能体在异步动作与观测中更灵活地决策。
Engagement Process: Rethinking the Temporal Interface of Action and Observation
- 将动作和观测视为独立的时间事件流，打破固定步长限制
- 在实验中揭示了传统框架隐藏的时序行为，并支持时间成本下的策略自适应
- 适合研究延迟反馈、持续动作等复杂时序场景的学者
数字与物理环境中的任务完成越来越依赖复杂的时序交互，动作与观测在不同时间尺度上展开，而非固定步长对齐。为此，我们提出“参与过程”（Engagement Process, EP），一种继承部分可观马尔可夫决策过程（POMDP）决策理论结构但显式建模时间的交互形式。EP将动作与观测表示为沿时间轴解耦的事件流，而非固定决策步上的成对更新。该接口能捕捉单智能体的延迟思考、延迟反馈、持续动作等时序问题，同时支持更丰富的智能体内部组织、多速率协同及子系统间的组合式交互。在玩具模型、大语言模型智能体及学习实验中，EP揭示了步骤式接口掩盖的时序行为，并使策略能在明确的时间成本下实现自适应。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。