Stanford's Bo Liu to present SPIRAL, SPICE, SPADE: self-play environments for recursive self-improvement

_AndrewZhao · x · 2026-09-21

Qingke Talk #156 (Sept 23, 10:00 AM Beijing time) will feature Stanford PhD student Bo Liu presenting three papers: SPIRAL, SPICE, and SPADE, and discussing when self-improvement counts as recursive self-improvement.

The core idea behind SPADE: continuous self-improvement needs an ever-expanding supply of training environments. SPADE has one model self-play both the Environment Designer and the Reasoning Agent, writing executable, agentic environments that get progressively harder — environment scaling on its own.

Original post →

More from Research

Research channel →