跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26491 · v1

FLUID: Flexible, Evidence-Grounded Situated Task Guidance

FLUID:灵活、基于证据的情境化任务指导

首次提交 2026-11-20 01:45
版本更新 2026-11-20 01:45
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

摘要

Real-time task guidance is inherently flexible: when an agent guides a user through a task, multiple responses and timings can be appropriate, and sometimes the best action is to remain silent. Existing benchmarks often miss this flexibility by treating synthesized dialogues as fixed targets for what to say and when to say it. We introduce FLUID (Flexible, Evidence-Grounded Situated Task Guidance), a unified framework for modeling, evaluating, and enabling flexible interaction in multimodal task guidance. Using naturally occurring human-human guidance from WTaG and HoloAssist, FLUID grounds interventions in their supporting evidence, necessity, and timing flexibility, and uses this representation both to evaluate flexible guidance and to build a real-time agent for task guidance. Our agent achieves the strongest overall balance of response correctness, intervention precision, timely guidance, and response latency among evaluated systems, while still leaving room for improvement in avoiding speech overlap. Together, FLUID moves situated task guidance beyond rigid reference matching toward more natural and adaptive human-AI interaction. Project page: https://fluid-guidance.github.io.

AI 论文解读

基于摘要 · 非全文审阅

提出统一框架 FLUID,用真实人际指导数据把干预建立在证据、必要性与时机灵活性上,既用于评估灵活指导,也用于构建实时指导智能体。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-20 01:45 · 最新观测版本

FLUID: Flexible, Evidence-Grounded Situated Task Guidance

Real-time task guidance is inherently flexible: when an agent guides a user through a task, multiple responses and timings can be appropriate, and sometimes the best action is to remain silent. Existing benchmarks often miss this flexibility by treating synthesized dialogues as fixed targets for what to say and when to say it. We introduce FLUID (Flexible, Evidence-Grounded Situated Task Guidance), a unified framework for modeling, evaluating, and enabling flexible interaction in multimodal task guidance. Using naturally occurring human-human guidance from WTaG and HoloAssist, FLUID grounds interventions in their supporting evidence, necessity, and timing flexibility, and uses this representation both to evaluate flexible guidance and to build a real-time agent for task guidance. Our agent achieves the strongest overall balance of response correctness, intervention precision, timely guidance, and response latency among evaluated systems, while still leaving room for improvement in avoiding speech overlap. Together, FLUID moves situated task guidance beyond rigid reference matching toward more natural and adaptive human-AI interaction. Project page: https://fluid-guidance.github.io.

查看此版本解读 →查看此版本原文 ↗