analiza aiqbench
This paper introduces the Engagement Process (EP), a formalism that decouples actions and observations into continuous event streams to better model real-world temporal dynamics like deliberation latency and delayed feedback. By moving beyond fixed decision steps, EP enables policies to adapt to explicit time costs and supports richer coordination among subsystems. The approach is validated across toy problems, LLM agents, and learning experiments, offering a more realistic framework for complex digital and physical environments.
Engagement Process: Rethinking the Temporal Interface of Action and Observation
arXiv:2605.11484v2 Announce Type: replace Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2605.11484 [cs.AI]
(or arXiv:2605.11484v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.11484 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 216 cuvinte
Subiecte conexe
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
Salesforce after Dreamforce: How the CRM giant can grow beyond its own interface
SiliconANGLE · 19 sept. 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
AI governance moves from observability to provable control
SiliconANGLE · 19 sept. 2026