Metraipolis › archive › dc_07c2ea3f475e
PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation — arXiv:2610.04916
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04916
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:31.669Z
- SHA-256 of the archived text
c70257ebe8d042d4f079d237b7e45a457d972679ba8fe5804b5bf81142bcfed5- Stable URL of this page
https://metraipolis.com/documento/dc_07c2ea3f475e
How to cite
PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation — arXiv:2610.04916 — arXiv, https://arxiv.org/abs/2610.04916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07c2ea3f475e (Metraipolis archive dc_07c2ea3f475e, sha256 c70257ebe8d042d4f079d237b7e45a457d972679ba8fe5804b5bf81142bcfed5)
BibTeX
@misc{dc07c2ea3f475e,
title = {PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation — arXiv:2610.04916},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04916},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07c2ea3f475e; sha256 c70257ebe8d042d4f079d237b7e45a457d972679ba8fe5804b5bf81142bcfed5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agentic navigation methods often struggle to translate distant goals into coherent local decisions in large-scale physical environments. Their reliance on linguistic reasoning over transient observations or limited history constrains anticipation of the consequences of actions and future conditions, despite the importance of such foresight for navigating long and complex urban routes. To bridge this gap, we propose PreAct-Nav, an agentic navigation framework that equips frozen policies with anticipatory reasoning for robust urban navigation. Our central idea is to anchor local decisions in persistent medium-horizon subgoals, assess the consequences of predicted actions before execution, and continually update the reasoning context using actual outcomes. At its core, a navigation memory module maintains the active subgoal and relevant experience across decisions, translating distant goals into actionable intermediate objectives. We further introduce a predictive world sandbox that uses an action-conditioned world model (AC-WM) to forecast world dynamics conditioned on candidate movements. A vision-language model (VLM) reasoner interprets these predictions under the current subgoal to retain or revise actions. After execution, real observations are used to assess outcomes, correct inconsistent assumptions, and update memory to continue or reformulate the subgoal. Extensive evaluations demonstrate that the proposed PreAct-Nav improves action selection through memory updates and visual prediction, with more pronounced gains on longer routes and routes with more turns. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04916 — 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 2026-10-06T05:24:05.933Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).