Color variation across histopathology slides remains one of the most stubborn sources of noise in computational pathology. Different scanners, staining protocols, and laboratories produce images that look systematically different even when the underlying tissue is similar. This batch effect degrades the performance of AI models, especially foundation models trained across multiple institutions.

Classical stain normalization methods (Histogram Matching, Macenko, Reinhard) are training-free, interpretable, and effective. The problem is speed. Existing implementations process images sequentially or fail to fully exploit modern GPUs, making them impractical for the tens of thousands of tiles that make up large whole-slide image cohorts.

A new agentic framework called SPARK uses language as a universal interface to autonomously generate biologically meaningful hypotheses and convert them into analytical tools directly from routine H&E pathology slides.

No hand-crafted features or task-specific retraining are required. The multi-agent system handles the full pipeline: