Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework
2026-07-01 • Computation and Language
Computation and LanguageArtificial IntelligenceHuman-Computer Interaction
AI summaryⓘ
The authors explain that conversational agents powered by large language models can change user behavior by acting like different types of personalities or roles. They found that using a moderate personality works best for trust and enjoyment, and changing the agent's role to fit the situation helps users more than keeping it the same all the time. Because conditions and user needs change, the authors suggest a Fluid Personality Framework that adapts both the agent's role (like coach or tutor) and how strongly its personality shows, based on the task and user context. This framework is designed to make interactions smoother and more effective.
large language modelsconversational agentspersonapersonality expressionmetaphorgoal-oriented tasksuser experiencebehavior changecontext adaptationFluid Personality Framework
Authors
Hasibur Rahman, Smit Desai
Abstract
Large language model (LLM)-based conversational agents (CAs) are now ubiquitous, creating new opportunities for AI-mediated behavior change. Their capacity to project nuanced personalities and adopt diverse metaphorical roles raises a design question: how should an agent's persona and personality be calibrated to the moment? Recent evidence suggests that (i) moderate personality expression outperforms low or high extremes on trust, enjoyment, and intention to adopt in goal-oriented tasks, and (ii) context-appropriate metaphors outperform static one-note assistants on user experience and uptake. Yet most CAs still fix both persona and style, risking misalignment when dynamics, urgency, and formality vary, for example in medical information seeking, fitness coaching, and reflective learning. We propose a Fluid Personality Framework that jointly adapts (1) the agent's metaphorical persona, such as coach, tutor, librarian, or tool, and (2) its personality expression intensity, low, medium, or high, as a function of task context, user goals and traits, and situational urgency. We sketch the framework and its core design dimensions.