SPADE: Auto-generating progressively harder training environments for self-improving agents
_AndrewZhao · x · 2026-08-21
Introduces the SPADE framework, where a single model acts as both the Environment Designer and the Reasoning Agent. It writes executable, agentic environments that increase in difficulty as the agent improves, enabling automatic environment scaling for continuous self-improvement.
More from Research
- Researcher publishes 8 months of primary-source records on frontier model behavior — rayanpal_ · 2026-08-21
- Solo dev trains 250M model SHADOW: 60 MB total, 400 tok/s on laptop CPU, 100M-token retrieval archive — Final-Data-1410 · 2026-08-21
- Hydra-0: a generalist world model that represents robot actions as action flow — mangahomanga · 2026-08-21
- Does Claude perform better in 'claudish'? Researchers call for empirical measures — voooooogel · 2026-08-21
- Sakana's DiffusionBlocks trains networks block-by-block, cutting memory up to 4x — z_latent · 2026-08-21
- Re-evaluation: memory-based self-improving agents ride on noise and task order — dair_ai · 2026-08-21