Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
This addresses the problem of time-consuming illustration creation for AI researchers, though it appears incremental as it builds on existing drawing practices and multi-agent frameworks.
The paper tackles the labor-intensive process of generating method illustrations for AI scientific papers by proposing FigAgent, a multi-agent framework that automatically creates high-quality illustrations through reusable drawing middlewares and an Explore-and-Select strategy, with extensive experiments demonstrating its efficacy.
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.