SCALE (Scalable Cross-Attention Learning with Extrapolation

SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling

arXiv:2606.06820v1 Announce Type: new Abstract: Agentic Large Language Model (LLM) systems decompose complex tasks into workflow Directed Acyclic Graphs (DAGs) whose primitives must be scheduled on heterogeneous clusters. Existing deep reinforcement learning (DRL) schedulers are tied to a fixed cluster size and require retraining whenever the number of servers changes. We propose SCALE (Scalable Cross-Attention Learning with Extrapolation), a DRL scheduler that generalizes to unseen cluster...