SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published 4 days ago • 47
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents Paper • 2602.13379 • Published Feb 13 • 3
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published 4 days ago • 47
SPADE Collection The full SPADE release: paper, model checkpoints, grounding corpora, and synthetic environments. • 4 items • Updated 3 days ago • 1
SPADE Synthetic Environments Collection The environments SPADE generated during training, and the GPT-5.5 pools used as the fixed baseline. • 4 items • Updated 3 days ago • 1