List your company

Multi-Agent Strategic Reasoning on Kuhn Poker In-domain

65.6Success RateGiGPO
59.15260.82662.564.174Mar 4, 2026

Evaluation results

MethodLinks
GiGPOCategory=RL2026.0365.6
MAGECategory=Meta-RL2026.0365.6
ReActCategory=In-Context Learning2026.0364.8
ReflexionCategory=In-Context Learning2026.0364.8
GRPOCategory=RL2026.0364.8
A-MEMCategory=Memory-based2026.0364.1
MementoCategory=Memory-based2026.0364.1
LAMERCategory=Meta-RL2026.0359.4