Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading only the agent's observable behavior are barely better than chance. We turn this signal into a practical abort cascade: one distribution-free calibrated g
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%langwatch/langwatch →
- PossiblePossibly related (embedding) · 54%agentscope-ai/Trinity-RFT →
- PossiblePossibly related (embedding) · 53%Yuqi-Zhou/LRAT →
- PossiblePossibly related (embedding) · 53%sandst1/remind →
- PossiblePossibly related (embedding) · 53%Evaluating long-term memory limits in stateless LLM chatbots — feedback needed [D] →
- LinkedLinked via arxiv author · 85%Kai Ruan →
“Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade”
- LinkedLinked via arxiv author · 85%Zihe Huang →
“Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade”
- LinkedLinked via arxiv author · 85%Ziqi Zhou →
“Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade”