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.
More from Research
- Jev's eval abstraction maps 1:1 to autorubric paper from 8 months ago, researcher finds — deliprao · 2026-09-21
- Researcher Says TypeSafe's Jev Mirrors His Autorubric LLM Eval Framework From 8 Months Ago — deliprao · 2026-09-21
- As ICLR 2027 Tops 60K Submissions, Researcher Proposes 3-4 Paper Cap per Author — ziv_ravid · 2026-09-21
- ICLR 2027 Hits 60K+ Submissions; Researcher Proposes Paper Caps, Forced Reproducibility — ziv_ravid · 2026-09-21
- No, Laya isn't capped at 512 tokens — it's ModernBERT with 8192-token configs — antoine_chaffin · 2026-09-21
- Kev open-source decision models scale to 0.6B/4B/8B, trainable in 40 min on one H100 — TheMoonMidas · 2026-09-21