GenFaceUI: Meta-Design of Generative Personalized Facial Expression Interfaces for Intelligent Agents

2026-02-11

AI Summary

This work proposes the first meta-design framework for generative facial expression interfaces (GPFEI), addressing key challenges in controllability, consistency, and contextual alignment when agents generate facial expressions at runtime. Centered on designers, GPFEI integrates character identity, context-to-expression mapping rules, and a semantic labeling system to support template creation, rule definition, and interactive iteration. Leveraging generative design methodologies and a prototype tool, the framework significantly enhances the controllability and consistency of expression generation. Qualitative evaluation with twelve designers validates its effectiveness and highlights the need for structured visual mechanisms and lightweight interpretability to support design workflows.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This work investigates generative facial expression interfaces for intelligent agents from a meta-design perspective. We propose the Generative Personalized Facial Expression Interface (GPFEI) framework, which organizes rule-bounded spaces, character identity, and context--expression mapping to address challenges of control, coherence, and alignment in run-time facial expression generation. To operationalize this framework, we developed GenFaceUI, a proof-of-concept tool that enables designers to create templates, apply semantic tags, define rules, and iteratively test outcomes. We evaluated the tool through a qualitative study with twelve designers. The results show perceived gains in controllability and consistency, while revealing needs for structured visual mechanisms and lightweight explanations. These findings provide a conceptual framework, a proof-of-concept tool, and empirical insights that highlight both opportunities and challenges for advancing generative facial expression interfaces within a broader meta-design paradigm.

Problem

• facial expression generation
• intelligent agents
• controllability
• coherence
• alignment

Innovation

• generative facial expression
• meta-design
• intelligent agents
• context-expression mapping
• designer-in-the-loop