Flight Recommendation on Flight Rec.
0.36RewardFixed Round
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Fixed Roundtau=42026.01 | 0.36 | 4 | 32 | 16 | |
| VOItau=0.012026.01 | 0.36 | 1.49 | 35 | 28 | |
| Fixed Roundtau=32026.01 | 0.35 | 3 | 32 | 20 | |
| Fixed Roundtau=22026.01 | 0.32 | 2 | 30 | 22 | |
| VOIBackbone=Gemini-2.5-Flash, tau=0.012026.01 | 0.3 | 1.62 | 28 | 22 | |
| VOItau=0.052026.01 | 0.29 | 0.82 | 29 | 25 | |
| VOIBackbone=Gemini-2.5-Flash, tau=0.052026.01 | 0.28 | 1.07 | 27 | 23 | |
| ConfidenceBackbone=Gemini-2.5-Flash, tau=0.92026.01 | 0.25 | 1.53 | 24 | 17 | |
| Confidencetau=0.92026.01 | 0.24 | 2.82 | 21 | 10 | |
| Confidencetau=0.72026.01 | 0.23 | 1.09 | 22 | 17 | |
| AdaptiveBackbone=Gemini-2.5-Flash2026.01 | 0.22 | 0.21 | 22 | 21 | |
| Fixed Roundtau=12026.01 | 0.22 | 1 | 21 | 17 | |
| Fixed RoundBackbone=Gemini-2.5-Flash, tau=42026.01 | 0.21 | 4 | 17 | 1 | |
| ConfidenceBackbone=Gemini-2.5-Flash, tau=0.72026.01 | 0.2 | 0.99 | 19 | 15 | |
| Adaptive2026.01 | 0.2 | 0.56 | 20 | 17 | |
| Fixed RoundBackbone=Gemini-2.5-Flash, tau=32026.01 | 0.19 | 3 | 16 | 4 | |
| Confidencetau=0.52026.01 | 0.19 | 0.71 | 19 | 16 | |
| Fixed RoundBackbone=Gemini-2.5-Flash, tau=12026.01 | 0.18 | 1 | 17 | 13 | |
| Fixed RoundBackbone=Gemini-2.5-Flash, tau=22026.01 | 0.18 | 2 | 16 | 8 | |
| No Question2026.01 | 0.17 | 0 | 17 | 17 | |
| No QuestionBackbone=Gemini-2.5-Flash2026.01 | 0.16 | 0 | 16 | 16 | |
| ConfidenceBackbone=Gemini-2.5-Flash, tau=0.52026.01 | 0.14 | 0.09 | 14 | 14 |