English(EN) Inferring the Unspoken: Aligning Embodied Agents with Implicit Preferences

新基准评估AI智能体推断用户隐式偏好的能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员引入了一个名为“基于偏好的规划”（PbP）的新基准，用于评估具身智能体在多大程度上能够推断并遵循用户的隐式偏好。该基准包含5000个评估组和290项不同复杂度的偏好。提出的“推断未言之意”（InTU）框架，在生成动作计划之前，会先将从多模态演示中推断出的偏好进行语言化表达。实验表明，虽然智能体在处理显式偏好时表现良好，但在从行为中推断隐式偏好时，其性能会显著下降，突显了视觉到语义的偏好获取是关键瓶颈。 AI

影响识别出个性化具身AI的关键瓶颈，并提出语言作为一种可迁移的表征，以改善智能体与用户偏好的对齐。

排序理由该集群包含一篇详细介绍具身AI新基准和框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍具身AI新基准和框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Manjie Xu, Xinyi Yang, Wei Liang, Chi Zhang, Yixin Zhu · 2026-09-10 04:00

推断未言之意：使具身智能体与隐式偏好对齐

arXiv:2502.00858v4 Announce Type: replace Abstract: Natural-language instructions rarely specify every detail required for embodied action. An agent asked to ``prepare an apple,'' for example, must still determine whether to wash or cut it, where to place it, and in what order to…

本文如何被排名

报道来源 [1]

推断未言之意：使具身智能体与隐式偏好对齐

相关话题