List your company

measure-melting-point-known-sub on ScienceWorld 20 unseen variants (test)

97.5ReturnNaive
7.95631.20354.4577.697Feb 26, 2026

Evaluation results

MethodLinks
NaiveBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Naive, Memory usage at test time=None2026.0297.5
EMPO2Backbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.0227.6
RetrospexBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Offline RL, Memory usage at test time=None2026.0226.5
GRPOBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.0219.8
ReflexionBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Non-Parametric, Memory usage at test time=None2026.0211.4