Procedure Planning on COIN T=3 (test)
30.12SRPDPP
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PDPPHorizon=32023.03 | 30.12 | 0.5095 | 59 | — | |
| P3IVHorizon=32023.03 | 15.4 | 0.2167 | 76.31 | — | |
| DDNHorizon=32023.03 | 13.9 | 0.2019 | 64.78 | — | |
| RetrievalHorizon=32023.03 | 4.38 | 0.174 | 32.06 | — | |
| LAPKEPP setting=true, Intermediate visual observations=false2026.03 | 0.4443 | 0.6808 | — | 66.71 | |
| ViterbiPlanNetParams (M)=6.672026.03 | 0.3399 | 0.5087 | 0.8388 | — | |
| PlanLLMParams (M)=386.432026.03 | 0.3344 | 0.5105 | 0.8466 | — | |
| PlanLLMKEPP setting=true, Intermediate visual observations=true2026.03 | 0.3322 | 0.5433 | — | — | |
| SCHEMAParams (M)=6.282026.03 | 0.3289 | 0.5084 | 0.8398 | — | |
| SCHEMAKEPP setting=true, Intermediate visual observations=false2026.03 | 0.3209 | 0.4984 | — | — | |
| MTIDKEPP setting=true, Intermediate visual observations=false2026.03 | 0.3044 | 0.517 | — | 59.74 | |
| LAP-TextKEPP setting=true, Intermediate visual observations=false2026.03 | 0.2706 | 0.5006 | — | 52.43 | |
| SkipPlan2024.03 | 0.2365 | 0.4712 | — | — | |
| SkipPlan2024.03 | 0.2365 | 0.4712 | 0.7844 | — | |
| SkipPlanKEPP setting=true, Intermediate visual observations=false2026.03 | 0.2365 | 0.4712 | — | — | |
| PDPPParams (M)=42.902026.03 | 0.2237 | 0.446 | 0.83 | — | |
| PDPPKEPP setting=true, Intermediate visual observations=false2026.03 | 0.2133 | 0.4562 | — | 51.82 | |
| KEPPR=22024.03 | 0.2025 | 0.3987 | — | — | |
| KEPPR=22024.03 | 0.2025 | 0.3987 | 0.5172 | — | |
| KEPPKEPP setting=true, Intermediate visual observations=false2026.03 | 0.2025 | 0.3987 | — | — | |
| E3P2024.03 | 0.1957 | 0.3142 | — | — | |
| E3P2024.03 | 0.1957 | 0.3142 | 0.8495 | — | |
| PDPP2024.03 | 0.1942 | 0.4344 | — | — | |
| PDPP2024.03 | 0.1942 | 0.4344 | 0.5003 | — | |
| Gemini 2.5 ProParams (M)=>100,0002026.03 | 0.1702 | 0.3887 | 0.7873 | — | |
| P3IV2024.03 | 0.154 | 0.2167 | — | — | |
| P3IV2024.03 | 0.154 | 0.2167 | 0.7631 | — | |
| Qwen2.5-32BParams (M)=32,0002026.03 | 0.1497 | 0.3634 | 0.7874 | — | |
| Qwen3-30B + PKGParams (M)=30,000, PKG=true2026.03 | 0.1463 | 0.3653 | 0.7811 | — | |
| Qwen3-30BParams (M)=30,0002026.03 | 0.1452 | 0.3656 | 0.7807 | — | |
| DDN2024.03 | 0.139 | 0.2019 | — | — | |
| DDN2024.03 | 0.139 | 0.2019 | 0.6478 | — | |
| KEPPParams (M)=44.662026.03 | 0.1385 | 0.284 | 0.6254 | — | |
| PKG beam searchParams (M)=42.902026.03 | 0.1332 | 0.3742 | 0.7893 | — | |
| Retrieval2024.03 | 0.0438 | 0.174 | — | — | |
| Retrieval2024.03 | 0.0438 | 0.174 | 0.3206 | — | |
| Qwen2.5-VL-32BParams (M)=32,0002026.03 | 0.0365 | 0.1751 | 0.521 | — | |
| RandomHorizon=32023.03 | 0.01 | 0.0001 | 2.47 | — | |
| Random2024.03 | 0.0001 | 0.0001 | — | — | |
| Random2024.03 | 0.0001 | 0.0001 | 0.0247 | — |