Agentic Search Benchmarks Average
58Average Token-level F1PDA-GAM
Evaluation Results
| Method | Links | |
|---|---|---|
| PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.05 | 58 | |
| PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.05 | 57.4 | |
| PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=32026.05 | 57.4 | |
| PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=32026.05 | 57.1 | |
| PDA-AveragingStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.05 | 56.9 | |
| PDA-KnOTSStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.05 | 56.8 | |
| PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.05 | 56.2 | |
| PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.05 | 56 | |
| PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=32026.05 | 55.9 | |
| PDA-AveragingStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.05 | 55.7 | |
| PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=32026.05 | 55.7 | |
| PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.05 | 55.5 | |
| PDA-KnOTSStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.05 | 55.5 | |
| PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.05 | 54.8 | |
| PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.05 | 54.3 | |
| Search-R1Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.05 | 53.7 | |
| PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.05 | 53.7 | |
| Qwen3Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.05 | 52.9 | |
| Joint ORPOStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.05 | 52.8 | |
| Search-R1Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.05 | 52.3 | |
| AceSearcherStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.05 | 51.9 | |
| Joint ORPOStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.05 | 51.7 | |
| Qwen3Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.05 | 51.3 | |
| Llama-3.2Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.05 | 50.9 | |
| Student BaselineStudent Model=Qwen3-8B2026.05 | 50.7 | |
| AceSearcherStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.05 | 50.3 | |
| Llama-3.2Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.05 | 49.2 | |
| Student BaselineStudent Model=Tülu3-8B2026.05 | 48.7 | |
| Sequential ORPOStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.05 | 47.9 | |
| Sequential ORPOStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.05 | 45.2 |