Stanford's Liu Bo to present SPIRAL/SPICE/SPADE self-play research

Stanford PhD student Liu Bo will present SPIRAL, SPICE and SPADE in a livestream on Sept 23, covering self-play approaches that let LLMs generate progressively harder training signals and improve recursively without human labels.

2026-09-21 ~ 2026-09-21 · 2 related posts

• Stanford's Bo Liu to present SPIRAL, SPICE, SPADE: self-play environments for recursive self-improvement — _AndrewZhao · 2026-09-21
• Self-Play Trio SPIRAL, SPICE, SPADE Push LLM Reasoning Up 5-10% Without Human Labels — 青稞AI · 2026-09-21