Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher ImpactResearchOct 5, 2026
When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarityResearchOct 5, 2026
Escaping the Capacity Ceiling: Routing on the Stiefel Manifold for Bilinear SPD LayersResearchOct 5, 2026
UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement LearningResearchOct 5, 2026
SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional PressureResearchOct 5, 2026
Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI AgentResearchOct 5, 2026