When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

arXiv:2606.05414 · cs.CL, cs.AI, cs.HC, cs.LG · Submitted 2026-06-03 · Read on arXiv

cs.CL, cs.AI, cs.HC, cs.LG

Submitted: 2026-06-03

Updated: 2026-10-30

Code: https://github.com/stonybrooknlp/appworld

Terminology

Sources

Related papers