test-conductivity-of-unknown-sub on ScienceWorld 20 unseen variants (test)
81.7ReturnNaive
Evaluation Results
| Method | Links | |
|---|---|---|
| NaiveBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Naive, Memory usage at test time=None2026.02 | 81.7 | |
| EMPO2Backbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.02 | 71.4 | |
| RetrospexBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Offline RL, Memory usage at test time=None2026.02 | 65.5 | |
| GRPOBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Online RL, Memory usage at test time=None2026.02 | 9.5 | |
| ReflexionBackbone=Qwen2.5-7B-Instruct, Learning Strategy=Non-Parametric, Memory usage at test time=None2026.02 | 2.6 |