Troubleshooting on FloDial Hard (test)
49Average Outcome RewardAREW– AS + BT
Evaluation Results
| Method | Links | |
|---|---|---|
| AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 49 | |
| AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 42.33 | |
| AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 42 | |
| AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 36 | |
| VANILLATraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 31 | |
| O4-MINITraining Protocol=DIRECT INFERENCE2026.03 | 26.33 | |
| VANILLATraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 21.33 | |
| LLAMA-3.1-8B-INST.Training Protocol=DIRECT INFERENCE2026.03 | 17.33 | |
| QWEN-2.5-7B-INST.Training Protocol=DIRECT INFERENCE2026.03 | 13.33 |