Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation
Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an under-specified 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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Who Pays? Personalization, Bossiness and the Cost of Fairness
Fairness-aware recommender systems that have a provider-side fairness concern seek to ensure that protected group(s) of providers have a fair opportunity to promote their items or products. There is a ``cost of fairness'…
FairnessRecommendation SystemsWhen Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation. However, adding agents in practice introduces inter-agent communicatio…
Community Detectiongraph partitioningAre LLMs Aware that Some Questions are not Open-ended?
Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware th…
Text GenerationOptimal valuation of American callable credit default swaps under drawdown of L\'evy insurance risk process
This paper discusses the valuation of credit default swaps, where default is announced when the reference asset price has gone below certain level from the last record maximum, also known as the high-water mark or drawdo…
The optimality of coarse categories in decision-making and information storage
An agent who lacks preferences and instead makes decisions using criteria that are costly to create should select efficient sets of criteria, where the cost of making a given number of choice distinctions is minimized. U…
Decision Making