Metraipolis › archive › dc_f49338ca35dc
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation — arXiv:2609.37353
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37353
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:23:48.080Z
- SHA-256 of the archived text
aabfcc18bf03d0548ca0b593c761493144abaf02dfe1a0cb8f25cc97ac88145f- Stable URL of this page
https://metraipolis.com/documento/dc_f49338ca35dc
How to cite
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation — arXiv:2609.37353 — arXiv (en), https://arxiv.org/abs/2609.37353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f49338ca35dc (Metraipolis archive dc_f49338ca35dc, sha256 aabfcc18bf03d0548ca0b593c761493144abaf02dfe1a0cb8f25cc97ac88145f)
BibTeX
@misc{dcf49338ca35dc,
title = {Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation — arXiv:2609.37353},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37353},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f49338ca35dc; sha256 aabfcc18bf03d0548ca0b593c761493144abaf02dfe1a0cb8f25cc97ac88145f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Navigation (VLN) requires agents to continuously ground task progress from long-horizon instructions and partial egocentric observations. Existing VLM-based navigation agents typically reason only over available observations and may remain confident even when task-relevant evidence is missing. For example, an agent may confidently proceed forward and get lost even though the landmark indicating the next turn lies outside its current field of view. We term this failure mode Progress Myopia: the agent fails to recognize unreliable progress grounding and continues acting on insufficient evidence. To address it, we propose SeekVLN, an evidence-seeking framework that couples semantic progress reasoning with active acquisition of task-relevant observations. SeekVLN is trained in two stages: First, Future-guided Reverse Generation (FRG) uses future expert actions to augment offline expert trajectories with supplementary views and evidence annotations. Supervised fine-tuning on these trajectories establishes a prior for evidence seeking and progress reasoning without additional expert interaction. However, imitation alone does not reveal whether seeking improves subsequent navigation. We therefore introduce Counterfactual Contrastive Policy Optimization (C2PO) for reinforcement fine-tuning. By comparing each evidence-seeking branch with a counterfactual direct-navigation branch from the same state, C2PO uses a contrastive reward to assign credit to seeking decisions based on subsequent navigation benefit. Experiments on simulated benchmarks show that SeekVLN achieves state-of-the-art performance, improving success rate by 12.7% and 7.5% over the base model on R2R-CE and RxR-CE, respectively. Both simulated and real-world evaluations exhibit human-like evidence-seeking behaviors for more reliable progress grounding. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.37353 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.618Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).