Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening Paper • 2602.05386 • Published 8 days ago • 69
FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments Paper • 2601.07853 • Published Jan 9 • 10
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published Jan 11 • 211