Skip to content

论文arXiv 2611.250052 天前

Inhabitant框架实现98.7%长程人机交互任务成功率 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Inhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative Feedback(arXiv 2611.25005)

核心内容 ​

针对现有语言模型Agent在长程人机交互(HSI)中缺乏空间控制与执行反馈导致任务失败的问题,研究提出免训练框架Inhabitant。该框架让Agent通过位置、路径和姿态显式指定动作,并测量执行偏差以修正控制参数。在包含31种家具布局、75项家庭任务的Inhabit基准上,结合Claude Opus 5.5模型实现了98.7%的任务完成率,显著优于Sonnet 5.5(93.3%)和Gemini 4 Argon(82.7%)。

Inhabit基准专为全身(不含手指)操作设计,每个任务链式包含1至3个可移动物体目标,用于评估复杂日常场景(如投掷玩具入篮)。消融实验证实,移除空间控制会导致大部分任务失败,缺失量化反馈则显著降低动作精度。该框架不依赖额外训练即可提升LLM对物理世界的操控粒度,代码已开源,为具身智能长序列任务规划提供了新的工程范式与评测标准。

关键看点 ​

  • 核心性能:Inhabitant框架搭配Claude Opus 5.5在Inhabit基准上达成98.7%任务完成率,Sonnet 5.5与Gemini 4 Argon分别为93.3%和82.7%
  • 技术机制:采用免训练架构,Agent通过位置/路径/姿态显式定义运动,并基于执行偏差的量化反馈实时修正控制规格
  • 基准构建:发布Inhabit数据集,涵盖31种公寓布局下的75项家庭任务,支持1-3个目标链式操作且限定全身(除手指)执行
  • 消融验证:实验确认空间控制模块是任务成功的关键前提,量化反馈机制直接决定动作执行的精确度

工程与产业观察 ​

该工作证明了在不进行微调的前提下,通过结构化空间约束与闭环量化反馈可充分释放大模型在长程具身任务中的潜力。Inhabit基准填补了全身操作评测空白,其“显式控制+偏差修正”范式为解决Sim-to-Real落地中的执行误差问题提供了低成本工程参考,对家庭服务机器人算法研发具有直接指导意义。

英文摘要 (Abstract) ​

Recent work on human-scene interaction (HSI) generation moves from single interactions to long-horizon interaction, where a language-model agent plans and executes a sequence of interactions in a 3D scene under one instruction. However, existing agents struggle in challenging everyday scenarios (e.g., picking up a toy and throwing it into a basket) because they lack spatial control over the motion and quantitative feedback on its execution, and they often fail to complete the interaction sequence. To address these gaps, we present Inhabitant, a training-free agent framework in which the agent specifies each motion through positions, paths and poses, measures how the executed interaction deviates from its intent, and revises the control specification accordingly. For an extensive evaluation in such scenarios, we build Inhabit, a benchmark of 75 household tasks in 31 furniture layouts of an apartment, in which every task chains one to three goals on movable objects and is carried out by the whole body, excluding fingers. On Inhabit, Inhabitant completes 98.7% of the tasks with Claude Opus 5.5, and 93.3% and 82.7% with Claude Sonnet 5.5 and Gemini 4 Argon, respectively. Ablations confirm that without spatial control the agent fails most tasks, and without quantitative feedback its motion becomes less precise. Code is available on the project page.

作者:Yao Zhang, Zhuchenyang Liu, Yu Xiao

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.25005:Inhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative Feedback ↗访问 2026-11-20