Metraipolis › archive › dc_439d6894e591
NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation — arXiv:2609.27526
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27526
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:53:39.727Z
- SHA-256 of the archived text
0568930e9e288cb2a3a683466334f19770ffe8468b3f8281f94ded9b77de6994- Stable URL of this page
https://metraipolis.com/documento/dc_439d6894e591
How to cite
NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation — arXiv:2609.27526 — arXiv (en), https://arxiv.org/abs/2609.27526 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_439d6894e591 (Metraipolis archive dc_439d6894e591, sha256 0568930e9e288cb2a3a683466334f19770ffe8468b3f8281f94ded9b77de6994)
BibTeX
@misc{dc439d6894e591,
title = {NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation — arXiv:2609.27526},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27526},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_439d6894e591; sha256 0568930e9e288cb2a3a683466334f19770ffe8468b3f8281f94ded9b77de6994},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27526. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, while compact summaries may omit details needed to reconsider earlier decisions. We introduce NavProbe, a hierarchical zero-shot navigation agent that couples a dynamic subgoal agenda with active evidence retrieval. A compact index links summaries of visited places, transitions, and landmarks to their visual and geometric records. When the current context is insufficient, a task executive retrieves targeted evidence to generate, revise, or resolve subgoals. Reusable conclusions are used to update the index, and a skill policy converts the revised task state into parameterized navigation actions. NavProbe achieves 71.7% SR and 55.8% SPL on R2R-CE and 55.3% SR and 38.6% SPL on RxR-CE, outperforming strong zero-shot baselines. It also achieves 79.3% SR on HM3D-v2 ObjectNav, with qualitative real-robot demonstrations illustrating physical deployment. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.27526 — 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 2026-10-08T12:21:19.482Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).