Inhabitant以空间控制执行长程家务交互
AI 总结
Yao Zhang、Zhuchenyang Liu和Yu Xiao于2026年11月18日向arXiv提交Inhabitant论文。该免训练智能体框架以位置、路径和姿态描述动作,衡量执行偏差并修订控制;配套的Inhabit基准包含31种公寓布局下的75项家务任务。作者报告Claude Opus 5.5、Claude Sonnet 5.5和Gemini 4 Argon的任务完成率分别为98.7%、93.3%和82.7%。
深度见解
Inhabitant把显式空间控制与定量反馈结合到长程具身交互中,并通过新的家务任务基准提供了具体研究对象。
Computer Science > Robotics
arXiv:2611.25005 (cs)
[Submitted on 18 Nov 2026]
Title:Inhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative Feedback
Authors:Yao Zhang, Zhuchenyang Liu, Yu Xiao
View a PDF of the paper titled Inhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative Feedback, by Yao Zhang and 2 other authors
#Inhabitant#Inhabit#Claude Opus 5.5#Claude Sonnet 5.5#Gemini 4 Argon