SPADE: Self-Play in Adaptive Synthetic Executable Environments
Bo Liu · hf · 2026-08-20
SPADE is a self-play reinforcement learning framework where an LLM designs adaptive executable training environments and learns to solve them. It improves reasoning and tool-use performance through regret-based environment targeting.
Related event: SPADE: Single-Model Self-Play Writes Its Own Training Environments(13 posts)→
More from Research
- 36 primitives, just 10 parameters each: a remarkably precise T-pose body fit — letandrewcook · 2026-10-16
- Interp researcher pushes back: if you can't simulate a neuron, you haven't explained it — nabla_theta · 2026-10-16
- MLP-Splatting (ECCV 2026) code released: MLPs as light-field primitives instead of Gaussians — AjdDavison · 2026-10-16
- Four-page solution to subcubic APSP builds intuition for Anthropic-AI-aided breakthrough — gautamcgoel · 2026-10-16
- ATAS: Zhejiang-led team builds world-state memory framework for consistent agentic video generation — CSProfKGD · 2026-10-16
- Hermes: a 4B model with 8K context got worse with more test-time compute, pointing to contextual reasoning — mangahomanga · 2026-10-16