Procedure Planning on NIV T=3 (test)
56.51SRLAP
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LAPTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 56.51 | 72.86 | — | 72.22 | |
| LAP-TextTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 43.87 | 65.55 | — | 66.16 | |
| ViterbiPlanNetParams (M)=5.482026.03 | 32.37 | 46.96 | 73.85 | — | |
| PDPPHorizon=32023.03 | 30.74 | 48.1 | 57.96 | — | |
| PlanLLMParams (M)=384.772026.03 | 30 | 44.35 | 73.6 | — | |
| MTIDTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 28.52 | 44.44 | — | 56.46 | |
| SCHEMATime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 27.93 | 41.64 | — | — | |
| KEPPParams (M)=41.862026.03 | 27.56 | 45.93 | 74.36 | — | |
| PlanLLMTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=true2026.03 | 26.74 | 42.97 | — | — | |
| PDPPParams (M)=41.742026.03 | 26.52 | 45.58 | 74.89 | — | |
| SCHEMAParams (M)=6.122026.03 | 26.3 | 42.77 | 73.04 | — | |
| E3P2024.03 | 26.05 | 51.24 | 75.81 | — | |
| Qwen3-30B + PKGParams (M)=30,000, PKG=true2026.03 | 25.19 | 43.95 | 71.98 | — | |
| PKG beam searchParams (M)=41.742026.03 | 24.96 | 43.46 | 72.18 | — | |
| Qwen3-30BParams (M)=30,0002026.03 | 24.81 | 42.84 | 70.8 | — | |
| P3IV2024.03 | 24.68 | 49.01 | 74.29 | — | |
| P3IVHorizon=32023.03 | 24.68 | 49.01 | 74.29 | — | |
| KEPP2024.03 | 24.44 | 43.46 | 86.67 | — | |
| KEPPTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 24.44 | 43.46 | — | — | |
| Qwen2.5-32BParams (M)=32,0002026.03 | 24.07 | 43.46 | 71.88 | — | |
| Gemini 2.5 ProParams (M)=>100,0002026.03 | 24.07 | 43.46 | 71.86 | — | |
| PDPP2024.03 | 22.22 | 39.5 | 86.66 | — | |
| PDPPTime horizon (T)=3, Data curation setting=KEPP, Intermediate visual observations=false2026.03 | 22.22 | 39.5 | — | — | |
| Ext-GAIL2024.03 | 22.11 | 42.2 | 65.93 | — | |
| Ext-GAILHorizon=32023.03 | 22.11 | 42.2 | 65.93 | — | |
| DDN2024.03 | 18.41 | 32.54 | 56.56 | — | |
| DDNHorizon=32023.03 | 18.41 | 32.54 | 56.56 | — | |
| Qwen2.5-VL-32BParams (M)=32,0002026.03 | 7.41 | 27.65 | 59.73 | — | |
| Random2024.03 | 2.21 | 4.07 | 6.09 | — | |
| RandomHorizon=32023.03 | 2.21 | 4.07 | 6.09 | — |