# GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design

arXiv: https://arxiv.org/abs/2609.02813 · HTML: https://mlsanity.com/paper/2609.02813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design](https://mlsanity.com/paper/2311.16974/) (2023)
- [Graphic Design with Large Multimodal Model](https://mlsanity.com/paper/2404.14368/) (2024)
- [CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers](https://mlsanity.com/paper/2604.19632/) (2026)
- [Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks](https://mlsanity.com/paper/2604.04192/) (2026)
- [From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design](https://mlsanity.com/paper/2602.13912/) (2026)

## Abstract (arXiv)

Text-to-image models excel at natural image synthesis but struggle with graphic design, where success depends on satisfying precise constraints on typography, layout, color, and visual communication. While prompt optimization offers an attractive alternative to expensive diffusion model fine-tuning, learning prompts for frozen image generators requires informative reward functions despite the entirely non-differentiable generation process. Reinforcement learning does not require differentiable objectives; it requires only scalar rewards capable of ranking candidate outputs. This raises a simple question: can design evaluation metrics themselves become reinforcement learning rewards? Our central contribution is GDB-Reward, a framework that systematically transforms heterogeneous graphic design evaluation metrics into a unified reinforcement learning reward. Experiments demonstrate that GDB-Reward provides an effective optimization objective, substantially improving adherence to the design specification in perceptual quality, rendering fidelity, and spatial accuracy while keeping the image generator entirely frozen. More broadly, our results demonstrate that heterogeneous, non-differentiable evaluation metrics can move beyond passive benchmarking to become effective optimization objectives for reinforcement learning in domains where differentiable supervision is unavailable.