Agentic Decision-Making on ALFWorld (Out-of-Distribution)
86.3Out-Success RateC-RF w/ NTF
Evaluation Results
| Method | Links | |
|---|---|---|
| C-RF w/ NTFModel=Qwen2.5-7B-Instruct, Type=RL Training2026.06 | 86.3 | |
| C-RF w/ NTFModel=Qwen2.5-1.5B-Instruct, Type=RL Training2026.06 | 77.9 | |
| GRPOModel=Qwen2.5-7B-Instruct, Type=RL Training2026.06 | 76.8 | |
| PPO (with critic)Model=Qwen2.5-7B-Instruct, Type=RL Training2026.06 | 76.2 | |
| RLOOModel=Qwen2.5-7B-Instruct, Type=RL Training2026.06 | 74 | |
| GRPOModel=Qwen2.5-1.5B-Instruct, Type=RL Training2026.06 | 70.1 | |
| RLOOModel=Qwen2.5-1.5B-Instruct, Type=RL Training2026.06 | 68.7 |