List your company

Troubleshooting on FloDial Easy (test)

44.33Average Outcome RewardAREW– AS + BT
23.5328.9334.3339.73Mar 12, 2026

Evaluation results

MethodLinks
AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.0344.33
AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.0343.67
AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.0341.67
AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.0341
VANILLATraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.0337.33
O4-MINITraining Protocol=DIRECT INFERENCE2026.0335
QWEN-2.5-7B-INST.Training Protocol=DIRECT INFERENCE2026.0324.33
LLAMA-3.1-8B-INST.Training Protocol=DIRECT INFERENCE2026.0324.33
VANILLATraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.0324.33