List your company
ResearchFormerly WizWand

Knowledge-Intensive Reasoning on WebWalker

30.5F1 ScoreLlama3.1-8B + ARPO
-0.77.415.523.6Dec 11, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Llama3.1-8B + ARPOBase Model=Llama3.1-8B, Algorithm=ARPO2025.1230.5
Llama3.1-8B + Reinforce ++Base Model=Llama3.1-8B, Algorithm=Reinforce ++2025.1227.5
Llama3.1-8B + GRPOBase Model=Llama3.1-8B, Algorithm=GRPO2025.1226.5
Qwen2.5-7B + Reinforce ++Base Model=Qwen2.5-7B, Algorithm=Reinforce ++2025.1226
Qwen2.5-7B + ARPOBase Model=Qwen2.5-7B, Algorithm=ARPO2025.1226
Llama3.1-8B + DAPOBase Model=Llama3.1-8B, Algorithm=DAPO2025.1225.5
Qwen2.5-3B + ARPOBase Model=Qwen2.5-3B, Algorithm=ARPO2025.1224.5
Qwen2.5-7B + DAPOBase Model=Qwen2.5-7B, Algorithm=DAPO2025.1224
Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, Algorithm=GRPO2025.1222
Qwen2.5-3B + GRPOBase Model=Qwen2.5-3B, Algorithm=GRPO2025.1221
Qwen2.5-3B + Reinforce ++Base Model=Qwen2.5-3B, Algorithm=Reinforce ++2025.1219.5
Qwen2.5-3B + DAPOBase Model=Qwen2.5-3B, Algorithm=DAPO2025.1219.5
Qwen2.5-7B + TIR PromptingBase Model=Qwen2.5-7B, Algorithm=TIR Prompting2025.1215.5
Llama3.1-8B + TIR PromptingBase Model=Llama3.1-8B, Algorithm=TIR Prompting2025.1215
Qwen2.5-3B + TIR PromptingBase Model=Qwen2.5-3B, Algorithm=TIR Prompting2025.1214
Llama3.1-8BBase Model=Llama3.1-8B, Algorithm=Direct Reasoning2025.123
Qwen2.5-7BBase Model=Qwen2.5-7B, Algorithm=Direct Reasoning2025.122
Qwen2.5-3BBase Model=Qwen2.5-3B, Algorithm=Direct Reasoning2025.120.5