{"ID":3004982,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-04T19:14:31.964469513Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03175","arxiv_id":"2606.03175","title":"Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation","abstract":"Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an underspecified natural-language description. Such ambiguity often cannot be resolved from perception and language alone, making interaction with an oracle a natural mechanism for disambiguation. Prior interactive methods allow oracle queries but treat lightweight clarification and route-level guidance alike, letting agents boost success rate through repeated high-information questions rather than by resolving the underlying ambiguity efficiently. We recast interactive IGN as a cost-sensitive uncertainty-reduction problem, where the agent should ask the question whose answer provides the largest reduction in navigation uncertainty relative to its penalty. To this end, we apply an information-gain analysis on existing navigation corpora to identify which cues reduce navigation uncertainty, yielding a compact set of question types and data-derived weights.However, existing interactive navigation benchmarks do not model the cost of different question types or evaluate how efficiently agents use interaction, making them unsuitable for studying cost-sensitive interaction. Based on this taxonomy, we construct a benchmark for diagnosing interaction behavior and efficiency, together with a Weighted Success Rate metric that penalizes each query by its derived cost. We further propose a zero-shot MLLM navigator that selectively queries at each decision step only when the expected uncertainty reduction justifies the interaction cost.","short_abstract":"Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an underspecified natural-language description. Such ambiguity often cannot be resolved from perception and language alone, making interaction with an oracle a natural mechanism for disambiguation. Prior...","url_abs":"https://arxiv.org/abs/2606.03175","url_pdf":"https://arxiv.org/pdf/2606.03175v1","authors":"[\"Xunyi Zhao\",\"Sihao Lin\",\"Gengze Zhou\",\"Zerui Li\",\"Shijie Li\",\"Wei Tao\",\"Jiajun Liu\",\"Qi Wu\"]","published":"2026-06-02T05:31:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Large Language Model\"]","has_code":false}