GraphicBench: A Planning Benchmark for Graphic Design with Language Agents
This addresses the need for better benchmarks in open-ended creative design for AI researchers, though it is incremental as it builds on existing agent frameworks.
The authors tackled the problem of evaluating LLM-powered agents in creative graphic design tasks by introducing GraphicBench, a benchmark with 1,079 queries across four design types, and found that while LLMs can generate workflows integrating constraints, they often fail in execution due to spatial reasoning and coordination challenges.
Large Language Model (LLM)-powered agents have unlocked new possibilities for automating human tasks. While prior work has focused on well-defined tasks with specified goals, the capabilities of agents in creative design tasks with open-ended goals remain underexplored. We introduce GraphicBench, a new planning benchmark for graphic design that covers 1,079 user queries and input images across four design types. We further present GraphicTown, an LLM agent framework with three design experts and 46 actions (tools) to choose from for executing each step of the planned workflows in web environments. Experiments with six LLMs demonstrate their ability to generate workflows that integrate both explicit design constraints from user queries and implicit commonsense constraints. However, these workflows often do not lead to successful execution outcomes, primarily due to challenges in: (1) reasoning about spatial relationships, (2) coordinating global dependencies across experts, and (3) retrieving the most appropriate action per step. We envision GraphicBench as a challenging yet valuable testbed for advancing LLM-agent planning and execution in creative design tasks.