Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing

Current LLM role-playing systems model persona as a monolithic, static attribute, conflating identity consistency with emotional rigidity. This leads to either robotic repetition or catastrophic persona drift under sustained interaction. We introduce Dynamic Persona Coherence, a framework that decouples Identity-Layer Stability (time-invariant traits) from Adaptive-Layer Appropriateness (history-dependent psychological evolution). We operationalize this through the L/M/S Psychological State Model, which represents persona dynamics across long-term identity, midterm meaning/stress accumulation, and shortterm affect. On top of this state representation, a closed-loop alignment system comprising an automated evaluator (Persona Consistency Critic, PCC), a selective repository (Persona Case Repository, PCR), and a trajectoryadjusting corrector (Persona Drift Suppressor, PDS) enables autonomous coherence repair. Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 demonstrate consistent improvements (+16-84% PCC gains). Code is available at https://anonymous.4open. science/r/DPC-30A1 .