Coverage (30d)
3vs1
This Week
3vs1
Evidence
1 articlesRelationships
1Timeline
SDAR2026-05-15
SDAR method achieves +9.4% on ALFWorld benchmark, improves WebShop and Search-QA
Ecosystem
Group Relative Policy Optimization (GRPO)
No mapped relationships
SDAR
usesGroup Relative Policy Optimization (GRPO)1 src