Design efficient event-driven job monitoring for agents
Design an agent-facing job-monitoring interface that delivers meaningful scheduler state changes efficiently, remains responsive, and avoids recreating the control-plane overhead of intensive polling.
References
An open question is therefore who should be responsible for monitoring jobs and how status updates should be delivered efficiently.
— Towards Efficient HPC Systems for Agents: Challenges and Opportunities
(2609.38723 - Zheng et al., 30 Sep 2026) in Section Compute, subsection “Opportunities: Trial-Aware, Hardware-Aware, and Event-Driven Scheduling”
Is a pull-mode binding worth standardising, given that adapters already cover unmodifiable agents? The single probe of Section~\ref{sec:probe} is a first step; a full binding would let the server also collect state from agents that never push.
— Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems
(2610.21538 - Gosmar et al., 15 Oct 2026) in Section 10, Open Issues, item 3