Aug 14, 2026 SPADE: Self-Play in Adaptive Synthetic Executable Environments Nov 3, 2025 SPICE: Self-Play In Corpus Environments Improves Reasoning Jul 5, 2025 SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning Feb 17, 2023 TorchOpt: An Efficient Library for Differentiable Optimization