List your company

identify-life-stages-2 on ScienceWorld 20 unseen variants (test)

56.3ReturnEMPO2
9.18821.41933.6545.881Feb 26, 2026

Evaluation results

MethodLinks
EMPO2Backbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.0256.3
NaiveBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Naive, Memory usage at test time=None2026.0250.7
GRPOBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.0239.5
ReflexionBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Non-Parametric, Memory usage at test time=None2026.0233.8
RetrospexBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Offline RL, Memory usage at test time=None2026.0211