Sequential Crafting on TextCraft-4
45.5Success Rate (SR)ReAct
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ReActn-shot summary setting=none, LLM Backbone=gpt-4o-mini2026.04 | 45.5 | 23.4 | 1.9 | |
| Gen-Cycn-shot summary setting=none, LLM Backbone=gpt-4o-mini2026.04 | 36.4 | 69.1 | 0.5 | |
| Spec-Cycn-shot summary setting=none, LLM Backbone=gpt-4o-mini2026.04 | 15.2 | 68.8 | 0.2 | |
| DepDAGn-shot summary setting=none, LLM Backbone=gpt-4o-mini2026.04 | 0 | — | — |