One Agent, Many Stains: Agentic Ensemble Design for Multi-Stain Computational Pathology

Pathological diagnosis routinely relies on multiple stains of the same tissue, including H&E and special or immunohistochemical stains, and multi-stain slide sets are increasingly available in digitized archives. Yet computational pathology models typically read a single stain or fuse stains using a single fixed architecture applied to every task, even though sections of different stains are unregistered and frequently missing, and labeled cohorts are small. We present ARISE (Agentic Rule Evolution for Integrating Stain-specific Experts), a simple and effective alternative: one well-trained multiple-instance model per stain is kept fixed, and the rule that integrates their predictions is designed separately for each task. ARISE builds a pool of candidate rules that abstain when a stain is missing and scores each candidate by its margin over the strongest conventional method. An LLM agent evolves the pool, the objective, and the search, while a numerical inner loop fits the weights. The output is a frozen program, a weighted list of pool members, that runs without an LLM or a GPU. We evaluate ARISE on four cohorts covering three organs (kidney, head and neck, lymphoma), panels of four to eight stains, both classification and time-to-event prediction, and one external site. The comparison methods, run under one protocol, include single-stain models, conventional ensembles, and published multi-stain fusion architectures. ARISE outperforms the strongest conventional method on every task in every cohort. On kidney biopsy lesion scoring, the margin holds in the internal cohort and at the external site (mean $\Delta$AUC $+0.014$ and $+0.037$, both $p<0.001$). Applied without modification, the same procedure improves head-and-neck survival and recurrence prediction ($\Delta$AUC $+0.009$ and $+0.032$) and lymphoma survival prediction ($\Delta$C-index $+0.035$). These results suggest that multi-stain integration can be treated as a task-specific design problem rather than a fixed architectural choice. ARISE provides a common procedure for constructing such integration programs across organs, stain panels, and prediction tasks.