Skip to main content
Search

Meta (United States)

2 related articles

Subscribe to updates
  1. medRxiv

    A breast cancer dual-ADC sequencing study ran end to end on an agentic workflow: 106 recorded cases, 63-day median second-drug span after T-DXd then SG

    A multi-agent workflow under investigator direction carried a large electronic health record study from cohort construction and executable statistics through data-quality checks, literature retrieval and reporting, using sequential sacituzumab govitecan (SG) and trastuzumab deruxtecan (T-DXd) orders in breast cancer as the clinical case. From 4.95 million patients, 106 had orders for both drugs, 73 with T-DXd first and 33 with SG first; median second-drug record spans were 63 and 49 days, a median difference of −14 days (95% CI, −41 to 21), descriptive and unadjusted.

  2. arXiv

    A new way to probe personal agents' cross-service risks: sampling a tool-dependency graph reaches a 19.2% average harmful path rate

    Instead of letting an LLM guess tool combinations from training memory, the red-teaming framework X-AgentRed samples cross-service paths from a tool-dependency graph, reaching a 19.2% average harmful path rate across four frontier agents in a simulated ecosystem of 30 services and 914 tools, above STAC's 10.5% and TRACE's 2.7%.

You’re all caught up