TRIAGE: Reliability- and Load-Conditioned Escalation for Two-Tier LLM Serving with a Semantic Evidence Judge

arXiv:2611.01174 · cs.LG, cs.CL, cs.DC, cs.PF · Submitted 2026-10-31 · Read on arXiv

cs.LG, cs.CL, cs.DC, cs.PF

Submitted: 2026-10-31

Updated: 2026-10-31

Terminology

Sources

Related papers