arXiv cs.AI
· Papers
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
arXiv:2607.06503v2 Announce Type: replace Abstract: Large language model (LLM) agents often waste inference compute by continuing multi-step trajectories that are already doomed to fail. We study early failure prediction and inference-time early stopping for LLM agents using hidden-state probes. Lightweight linear prob