PosterMate: Audience-driven Collaborative Persona Agents for Poster Design

2025-07-24

AI Summary

This study addresses the challenge of simultaneously acquiring and integrating diverse audience feedback in poster design. We propose an audience-driven, role-based agent collaboration framework. Methodologically, we pioneer the use of generative AI to construct identity-consistent, marketing-document-driven persona agents; a coordinator mechanism orchestrates multi-role deliberation, culminating in actionable design revision suggestions. Our contributions are twofold: (1) a deliberative interaction and feedback aggregation mechanism that synthesizes heterogeneous perspectives, and (2) empirical validation of AI-simulated user personas for effective collaborative design decision-making. A user study (N=100) demonstrates that our system significantly improves perspective coverage, reliably uncovers overlooked design issues, and yields persona feedback exhibiting high identity consistency and efficient viewpoint integration.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Poster designing can benefit from synchronous feedback from target audiences. However, gathering audiences with diverse perspectives and reconciling them on design edits can be challenging. Recent generative AI models present opportunities to simulate human-like interactions, but it is unclear how they may be used for feedback processes in design. We introduce PosterMate, a poster design assistant that facilitates collaboration by creating audience-driven persona agents constructed from marketing documents. PosterMate gathers feedback from each persona agent regarding poster components, and stimulates discussion with the help of a moderator to reach a conclusion. These agreed-upon edits can then be directly integrated into the poster design. Through our user study (N=12), we identified the potential of PosterMate to capture overlooked viewpoints, while serving as an effective prototyping tool. Additionally, our controlled online evaluation (N=100) revealed that the feedback from an individual persona agent is appropriate given its persona identity, and the discussion effectively synthesizes the different persona agents' perspectives.

Problem

• Gathering diverse audience feedback for poster design
• Reconciling conflicting design edits from multiple perspectives
• Simulating human-like interactions for design feedback processes

Innovation

• Generative AI simulates audience feedback personas
• Moderator-driven discussion synthesizes diverse design perspectives
• Direct integration of agreed edits into poster design