Vision-and-Language Navigation on R2R (val seen)
83.74Success Rate (SR)GOAT
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| GOAT2024.04 | 83.74 | 1.79 | 88.64 | 79.48 | — | — | — | — | — | |
| TSOR2026.03 | 82 | 2.05 | — | 76 | — | — | — | — | — | |
| VLN-BERTSpeaker=true, Follower=true2021.08 | 81.86 | 2.35 | 86.57 | 78 | — | — | — | — | 10.61 | |
| AirbertSpeaker=true, Follower=true2021.08 | 81.4 | 2.13 | 87.17 | 77 | — | — | — | — | 10.63 | |
| DSRG2024.04 | 81 | 2.23 | 88 | 76 | — | — | — | — | — | |
| BEVBert2024.04 | 81 | 2.17 | 88 | 74 | — | — | — | — | — | |
| BEVBertSetting=Cross-modal backbone, Year=20222026.01 | 81 | 2.17 | 88 | 74 | — | — | — | 13.56 | — | |
| ScaleVLNSetting=Cross-modal backbone, Year=2023, multi-task pretraining=true2026.01 | 81 | 2.12 | 87 | 75 | — | — | — | 13.24 | — | |
| BEVBert2026.02 | 81 | 2.17 | 88 | 74 | — | — | — | 13.56 | — | |
| ScaleVLN2026.02 | 81 | 2.12 | 87 | 75 | — | — | — | 13.24 | — | |
| KESU2026.03 | 81 | 2.19 | — | 75 | — | — | — | — | — | |
| BEVBert2026.03 | 81 | 2.17 | — | 74 | — | — | — | — | — | |
| BTK2026.03 | 81 | 2.09 | 88 | 75 | — | — | — | — | — | |
| GridMM2026.03 | 80 | 2.34 | — | 74 | — | — | — | — | — | |
| KERM2026.03 | 80 | 2.19 | — | 74 | — | — | — | — | — | |
| DUET2024.04 | 79 | 2.28 | 86 | 73 | — | — | — | — | — | |
| GeoVLN2024.04 | 79 | 2.22 | — | 76 | — | — | — | — | — | |
| DUETSetting=Cross-modal backbone, Year=20222026.01 | 79 | 2.28 | 86 | 73 | — | — | — | 12.32 | — | |
| DUET2026.02 | 79 | 2.28 | 86 | 73 | — | — | — | 12.32 | — | |
| DUET2026.03 | 79 | 2.28 | 86 | 73 | — | — | — | — | — | |
| CONSOLE2026.03 | 79 | 2.17 | — | 73 | — | — | — | — | — | |
| ViTeC2026.03 | 79 | 2.22 | — | 74 | — | — | — | — | — | |
| VLN-SIGVisual Features=CLIP-ViT/162023.04 | 78.6 | — | — | 74.8 | — | 81.8 | 72.2 | — | — | |
| HOP+2026.03 | 78 | 2.33 | — | 73 | — | — | — | — | — | |
| TD-STP2024.04 | 77 | 2.34 | 83 | 73 | — | — | — | — | — | |
| EnvEdit2024.04 | 77 | 2.32 | — | 74 | — | — | — | — | — | |
| TD-STP2026.03 | 77 | 2.34 | 83 | 73 | — | — | — | — | — | |
| HAMT2024.04 | 76 | 2.51 | 82 | 72 | — | — | — | — | — | |
| GELA2024.04 | 76 | 2.39 | — | 73 | — | — | — | — | — | |
| HAMTSetting=Cross-modal backbone, Year=20212026.01 | 76 | 2.52 | — | 72 | — | — | — | 11.15 | — | |
| HAMT2026.02 | 76 | 2.52 | — | 72 | — | — | — | 11.15 | — | |
| HAMT2026.03 | 76 | 2.34 | 82 | 72 | — | — | — | — | — | |
| Esceme2026.03 | 76 | 2.57 | — | 73 | — | — | — | — | — | |
| DUET-CLIPVisual Features=CLIP-ViT/162023.04 | 75.2 | — | — | 69.1 | — | 76 | 66.5 | — | — | |
| AirbertSpeaker=false, Follower=true2021.08 | 74.22 | 2.72 | 82.94 | 70 | — | — | — | — | 10.69 | |
| NavGPT-2Setting=Prompting-based LLM agents, Year=2024, additional synthetic trajectories=true2026.01 | 74 | 2.84 | 83 | 63 | — | — | — | 14.13 | — | |
| NavGPT22026.03 | 74 | 2.84 | 83 | 63 | — | — | — | — | — | |
| AirbertSpeaker=false, Follower=false2021.08 | 73.85 | 3.21 | 80.71 | 69 | — | — | — | — | 10.59 | |
| LSAL2026.03 | 73 | 2.88 | — | 70 | — | — | — | — | — | |
| VLN-BERTSpeaker=false, Follower=false2021.08 | 70.2 | 3.73 | 76.47 | 66 | — | — | — | — | 10.28 | |
| Speaker FollowerSetting=Cross-modal backbone, Year=20182026.01 | 66 | 3.36 | 74 | — | — | — | — | — | — | |
| SpeakerFollower2026.02 | 66 | 3.36 | 74 | — | — | — | — | — | — | |
| EnvDrop2026.03 | 62 | 3.99 | — | 59 | — | — | — | — | — | |
| Self-MonitoringTraining Paradigm=Naïve CL2021.11 | 61 | 4.08 | 69.8 | 54.6 | 64.9 | — | — | — | — | |
| Self-MonitoringTraining Paradigm=Naïve CL2021.11 | 61 | 4.08 | 69.8 | 54.6 | 64.9 | 66.2 | 53.9 | — | — | |
| Self-MonitoringTraining Paradigm=Self-Paced CL2021.11 | 58.8 | 4.19 | 68.2 | 53.3 | 65.4 | — | — | — | — | |
| Self-MonitoringTraining Paradigm=Self-Paced CL2021.11 | 58.8 | 4.19 | 68.2 | 53.3 | 65.4 | 66.3 | 52.2 | — | — | |
| FollowerTraining Paradigm=Self-Paced CL2021.11 | 58.7 | 4.23 | 69.2 | 51.1 | 63.3 | — | — | — | — | |
| FollowerTraining Paradigm=Self-Paced CL2021.11 | 58.7 | 4.23 | 69.2 | 51.1 | 63.3 | 64.5 | 50.5 | — | — | |
| Self-MonitoringTraining Paradigm=Machine Learning2021.11 | 58.4 | 4.27 | 67 | 51.9 | 64.1 | — | — | — | — | |
| Self-MonitoringTraining Paradigm=Base2021.11 | 58.4 | 4.27 | 67 | 51.9 | 64.1 | 65.4 | 51.5 | — | — | |
| EnvDropTraining Paradigm=Self-Paced CL2021.11 | 58.1 | 4.42 | 65.6 | 54.8 | 67.4 | — | — | — | — | |
| EnvDropTraining Paradigm=Self-Paced CL2021.11 | 58.1 | 4.42 | 65.6 | 54.8 | 67.4 | 67.7 | 51.6 | — | — | |
| EnvDropTraining Paradigm=Naïve CL2021.11 | 57.8 | 4.49 | 63.1 | 54.8 | 67.2 | — | — | — | — | |
| EnvDropTraining Paradigm=Naïve CL2021.11 | 57.8 | 4.49 | 63.1 | 54.8 | 67.2 | 67.5 | 51.5 | — | — | |
| EnvDropTraining Paradigm=Machine Learning2021.11 | 57.7 | 4.55 | 65.6 | 54.4 | 67.2 | — | — | — | — | |
| EnvDropTraining Paradigm=Base2021.11 | 57.7 | 4.55 | 65.6 | 54.4 | 67.2 | 67.2 | 51.4 | — | — | |
| DV-VLNSetting=Trainable language-only agents, Year=20252026.01 | 54 | 5.03 | 66 | 49 | — | — | — | 10.53 | — | |
| FollowerTraining Paradigm=Machine Learning2021.11 | 52.3 | 4.85 | 65.3 | 44.3 | 58.2 | — | — | — | — | |
| FollowerTraining Paradigm=Base2021.11 | 52.3 | 4.85 | 65.3 | 44.3 | 58.2 | 59.4 | 44.1 | — | — | |
| FollowerTraining Paradigm=Naïve CL2021.11 | 48.6 | 5.03 | 62 | 40.4 | 55.9 | — | — | — | — | |
| FollowerTraining Paradigm=Naïve CL2021.11 | 48.6 | 5.03 | 62 | 40.4 | 55.9 | 57.4 | 40.5 | — | — | |
| NavCoTSetting=Trainable language-only agents, Year=20252026.01 | 41 | 6.46 | 48 | 38 | — | — | — | 10.08 | — | |
| Seq2SeqSetting=Cross-modal backbone, Year=20182026.01 | 39 | 6.01 | 53 | — | — | — | — | 11.33 | — | |
| Seq2Seq2026.02 | 39 | 6.01 | 53 | — | — | — | — | 11.33 | — | |
| Seq2Seq2026.03 | 39 | 6.01 | — | — | — | — | — | — | — | |
| Retrieval-augmented LLM navigatorBackbone=Qwen3-8B2026.02 | 19.88 | 8.96 | 39.86 | 13.29 | — | — | — | 16.2 | — | |
| NavGPTBackbone=Qwen3-8B2026.02 | 15.77 | 8.81 | 29.87 | 10.3 | — | — | — | 15.29 | — | |
| EnvDrop2022.03 | — | — | — | — | 67.2 | 67.2 | — | — | — | |
| HOP2022.03 | — | — | — | — | 73.3 | 76.1 | — | — | — | |
| Self-Monitoring2022.03 | — | — | — | — | 64.1 | 65.4 | — | — | — | |
| Syntax2022.03 | — | — | — | — | 70 | 70 | — | — | — |