Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.18624v1</id>\n    <title>REST: Receding Horizon Explorative Steiner Tree for Zero-Shot Object-Goal Navigation</title>\n    <updated>2026-03-19T08:43:40Z</updated>\n    <link href='https://arxiv.org/abs/2603.18624v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.18624v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Zero-shot object-goal navigation (ZSON) requires navigating unknown environments to find a target object without task-specific training. Prior hierarchical training-free solutions invest in scene understanding (\\textit{belief}) and high-level decision-making (\\textit{policy}), yet overlook the design of \\textit{option}, i.e., a subgoal candidate proposed from evolving belief and presented to policy for selection. In practice, options are reduced to isolated waypoints scored independently: single destinations hide the value gathered along the journey; an unstructured collection obscures the relationships among candidates. Our insight is that the option space should be a \\textit{tree of paths}. Full paths expose en-route information gain that destination-only scoring systematically neglects; a tree of shared segments enables coarse-to-fine LLM reasoning that dismisses or pursues entire branches before examining individual leaves, compressing the combinatorial path space into an efficient hierarchy. We instantiate this insight in \\textbf{REST} (Receding Horizon Explorative Steiner Tree), a training-free framework that (1) builds an explicit open-vocabulary 3D map from online RGB-D streams; (2) grows an agent-centric tree of safe and informative paths as the option space via sampling-based planning; and (3) textualizes each branch into a spatial narrative and selects the next-best path through chain-of-thought LLM reasoning. Across the Gibson, HM3D, and HSSD benchmarks, REST consistently ranks among the top methods in success rate while achieving the best or second-best path efficiency, demonstrating a favorable efficiency-success balance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-19T08:43:40Z</published>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Shuqi Xiao</name>\n    </author>\n    <author>\n      <name>Maani Ghaffari</name>\n    </author>\n    <author>\n      <name>Chengzhong Xu</name>\n    </author>\n    <author>\n      <name>Hui Kong</name>\n    </author>\n  </entry>"
}