Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows
This work presents a tail-risk-aware turn release scheduling method that jointly decides which ready turn to release next and how much released but unfinished work to maintain, and reduces the P95 of workflow flow time under contention, achieving up to a \(3.50\times\) speedup.
Bo-Chao Feng, Jian-Jiang Li, Haojie Wang et al.
· 0 citations