llm-kb
← Back to research
Paper

SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction

Researchers propose SAGEAgent, a self-evolving agent that sequentially decides which diagnostic modalities to acquire for cancer survival prediction, balancing accuracy and cost. It follows the clinically mandated order of escalating burden, from demographics to genomic profiling. The agent actively reasons whether acquiring the next modality is justified for each patient, unlike current methods that assume all modalities are available or passively handle missing data.

0 engagement·1 source·Fri, Jul 10, 2026, 03:32 PM
The paper formulates modality acquisition as a sequential decision problem. SAGEAgent learns a policy to decide when to stop acquiring modalities, reducing unnecessary tests while maintaining prediction accuracy. This is particularly relevant for resource-constrained settings or when invasive procedures are involved. The approach is evaluated on multimodal survival prediction tasks, showing that it can achieve comparable performance to full-modality models with significantly fewer modalities.

Entities

SAGEAgent(tool)multimodal survival prediction(concept)cost-aware modality acquisition(concept)

Related