ProCompNav：用比较式判断解决模糊指令的主动实例导航框架
ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
AI 导读
ProCompNav 是一个面向人机交互中模糊指令的两阶段主动实例导航框架，先构建候选池，再通过递归比较式判断（RCJ）用二选一问题迭代缩小候选范围。该方法在交互式导航基准上显著提升成功率并缩短用户回复长度，在非交互基准上取得最高成功率。两项人类研究显示参与者更偏好其二选一提问和批量式交互，论文已被 NeurIPS 2026 接收为 Oral。
正文 · 原文
Abstract:In human-robot interaction, agentic robots should resolve ambiguous user requests through proactive clarification while keeping user burden low. We study this challenge in interactive instance navigation, where an agent must identify and reach the user-intended target among similar objects. Existing approaches ask open-ended questions and select a candidate that strongly matches the accumulated user-provided information. However, this process can require lengthy user responses and lead the agent to make premature decisions without distinguishing the target from distractors. To address these limitations, we propose Proactive Instance Navigation with Comparative Judgment (ProCompNav), a two-stage framework that first constructs a candidate pool and then identifies the target through Recursive Comparative Judgment (RCJ). RCJ iteratively narrows the pool by selecting an attribute-value pair that divides the candidates, asking the user a binary question, and removing inconsistent candidates, without requiring an attribute unique to the target. ProCompNav substantially improves Success Rate and reduces Response Length on an interactive navigation benchmark, and achieves the highest Success Rate among evaluated methods on a non-interactive benchmark. In two human studies, participants preferred ProCompNav's binary questions to open-ended questions and its batched delivery to interleaved interaction. Our results highlight the need to jointly consider task performance and user-friendly interaction strategies when designing agentic robots.
| Comments: | Accepted to NeurIPS 2026 (Oral), Project page: this https URL Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2605.06223 [cs.AI] |
| (or arXiv:2605.06223v5 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06223 arXiv-issued DOI via DataCite |
Submission history
From: Junhyuk Kwon [view email]
[v1]
Thu, 7 May 2026 13:19:03 UTC (1,271 KB)
[v2]
Fri, 8 May 2026 13:20:32 UTC (1,269 KB)
[v3]
Fri, 15 May 2026 10:32:27 UTC (2,094 KB)
[v4]
Tue, 29 Sep 2026 17:45:21 UTC (2,601 KB)
[v5]
Thu, 5 Nov 2026 18:29:02 UTC (4,232 KB)
来源：arXiv cs.AI · arxiv.org