SOURCE-LINKED INTELLIGENCE

TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored

Read original source ↗ Open in workspace

recordType

paper

region

Global