{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:30:46Z","timestamp":1773801046486,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Zero-shot object navigation tasks agents with locating target objects in unseen environments\u2014a core capability of embodied intelligence. While recent vision-language navigation methods leverage Large Language Models (LLMs) for multimodal reasoning, they suffer from two key limitations: (1) semantic misalignment between language-grounded maps and real-world layouts, and (2) inefficiency due to LLMs\u2019 lack of specialization for navigation-specific tasks. To address these challenges, we propose Chain-of-Search (CoS), a novel parameter-efficient framework that enables human-like decision-making via iterative semantic reasoning. First, CoS replaces traditional global maps with an optimal-benefit multi-map construction that continuously balances expected gain and cost throughout the navigation process. Second, we introduce a Parameter-Efficient Intent Aligner (PEIA), trained via a prompt-guided paradigm to align directional decisions with navigation intent. PEIA injects semantic cues into benefit-aware maps, enabling more rational and goal-consistent exploration. Finally, a Reflection-Guided Destination Verifier (RDV) confirms whether the target is reached via language-driven reasoning and corrects potential errors through self-reflection. CoS achieves state-of-the-art performance on HM3D (+2.8% SR) and MP3D (+1.2% SR) without relying on LLMs, demonstrating the effectiveness of lightweight, reasoning-centered navigation.<\/jats:p>","DOI":"10.1609\/aaai.v40i3.37150","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:56:46Z","timestamp":1773788206000},"page":"1721-1729","source":"Crossref","is-referenced-by-count":0,"title":["Chain-of-Search: Parameter-Efficient Reasoning for Zero-Shot Object Navigation"],"prefix":"10.1609","volume":"40","author":[{"given":"Hanrui","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangli","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37150\/41112","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37150\/41112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:56:47Z","timestamp":1773788207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37150"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i3.37150","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}