Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents Meta-Transfer Learning for mmWave Beam Alignment Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries