Preprint
Jul 2026
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
The proposed LLM agent early-stopping cascade outperforms the best single-gate baseline in every model-environment pair, saving 1.5-8.8 times more compute at a 90% recall target.
Kai Ruan, Zihe Huang, Ziqi Zhou et al.
· 1 citation