Papers

FLUID框架:让AI任务指导更灵活,学会适时沉默

FLUID: Flexible, Evidence-Grounded Situated Task Guidance

Why we picked it

这篇论文解决了一个容易被忽略的问题:AI实时指导你做事时,什么时候该说话、什么时候该闭嘴。它用真实的人人指导数据替代合成对话来评估系统,还给出了四项指标的综合基准结果。做语音助手、AR眼镜指导或具身交互的团队可以重点看看评估框架。

研究团队推出FLUID框架,用于建模和评估多模态任务指导中的灵活交互。该框架基于WTaG和HoloAssist两个自然人与人指导数据集,将AI干预锚定在支撑证据、必要性和时机弹性三个维度上。

Body

传统基准把合成的对话当作固定答案,只比对内容是否一致,忽略了同一时刻多种回应都合理、有时保持沉默才是最优选择这一现实。FLUID用统一的表征方式同时完成两件事:评估指导系统的灵活性,以及构建一个实时任务指导Agent。

作者报告其Agent在回应正确性、干预精准度、指导时机和响应延迟四项指标的综合平衡上优于所有被测系统,但在避免语音重叠方面仍有提升空间。这项工作把情境化任务指导从僵硬的参照匹配推向更自然的自适应交互。

Original · arXiv cs.AI

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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include FLUID, multimodal, agents, benchmarks.

Source attribution: curated from arXiv cs.AI (@Yunqi Zhao, Run Peng, Ze Dong, Ryan Lu, Yinpei Dai, Joyce Chai).