SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published 3 days ago • 44
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents Paper • 2602.13379 • Published Feb 13 • 3
SPADE Synthetic Environments Collection The environments SPADE generated during training, and the GPT-5.5 pools used as the fixed baseline. • 4 items • Updated 1 day ago
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published 3 days ago • 44