Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
RegLLM measures escalation, grounding, and unsafe actions for regulated agents, but only at smoke scale.
1 stories, newest first · one card per story
RegLLM measures escalation, grounding, and unsafe actions for regulated agents, but only at smoke scale.
Today 251 readers · 270 views · 20 reads · all time 108K views