TL;DR
The paper introduces an Agentic Design Review System that uses multiple collaborative agents, orchestrated by a meta-agent, to evaluate graphic designs holistically, backed by a new benchmark and experimental validation.
Contribution
It presents a novel multi-agent framework with in-context exemplar selection and prompt expansion for holistic graphic design evaluation, along with the DRS-BENCH benchmark.
Findings
AgenticDRS outperforms state-of-the-art baselines.
The framework provides actionable feedback.
Experimental results validate the approach's effectiveness.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
