Patrick Wilhelm

Identifiers

• name variant Patrick Wilhelm 0.60 · backfill

Papers (1)

1. From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cs.AI · 2026 · author #1

Mentions

• 2606.06223 #1 · arxiv_oai · confidence 0.70 Patrick Wilhelm

Frequent Coauthors

• Odej Kao 1 shared papers