SPADE: Self-Play Framework Generates Training Environments for Continuous Improvement

SPADE is a self-play RL framework where a language model both designs adaptive executable training environments and solves them, with difficulty scaling automatically. It improves reasoning and tool-use performance without manual curriculum expansion.

2026-08-20 ~ 2026-08-20 · 2 related posts

• SPADE: Self-Play in Adaptive Synthetic Executable Environments — Bo Liu · 2026-08-20
• SPADE enables AI continuous self-improvement via auto-generated environments — pliang279 · 2026-08-20