Agentic Design Review System

2025-08-14

AI Summary

This work addresses the lack of multi-dimensional collaborative analysis in automated graphic design evaluation. We propose a multi-agent collaborative review framework featuring a meta-agent that orchestrates specialized agents for composition, color harmony, and aesthetics. Crucially, we integrate graph-matching-driven contextual example selection with prompt expansion strategies to endow each agent with design-aware reasoning capabilities. Leveraging a multi-agent architecture, structured prompt engineering, and in-context learning, our framework delivers cross-dimensional, consistent, interpretable evaluations and actionable feedback. Evaluated on our newly constructed DRS-BENCH benchmark, it significantly outperforms existing methods. Ablation studies confirm the critical contributions of both graph-matching-based example selection and prompt expansion to assessment quality and feedback utility.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Metareasoning and Metaheuristics
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggregating feedback from individual expert reviewers. Towards this, we propose an Agentic Design Review System (AgenticDRS), where multiple agents collaboratively analyze a design, orchestrated by a meta-agent. A novel in-context exemplar selection approach based on graph matching and a unique prompt expansion method plays central role towards making each agent design aware. Towards evaluating this framework, we propose DRS-BENCH benchmark. Thorough experimental evaluation against state-of-the-art baselines adapted to the problem setup, backed-up with critical ablation experiments brings out the efficacy of Agentic-DRS in evaluating graphic designs and generating actionable feedback. We hope that this work will attract attention to this pragmatic, yet under-explored research direction.

Problem

• Evaluating graphic designs from multiple facets like alignment and aesthetics
• Aggregating feedback from individual expert reviewers holistically
• Proposing a benchmark for design review systems (DRS-BENCH)

Innovation

• Multi-agent collaboration orchestrated by meta-agent
• Graph matching for in-context exemplar selection
• Prompt expansion method enhances design awareness