Xi Zhang

Scientific agent swarms can achieve state-of-the-art performance and generalize to new tasks by evolving through feedback-guided mutation and complementary recombination of hypotheses and code.

Attackers can exploit lifecycle-hook updates to execute malicious commands with host privileges, compromising AI agent harnesses at alarming rates.

Storage limitations, not compute power, dictate the scalability of whole-slide image embedding extraction, reshaping our approach to handling large-scale medical data.