# RobotWorld：面向多样任务与具身形态的机器人使用多模态智能体基准测试

> 原文链接：https://robotics.hellobike.com/papers/2026-10-07-2610-10409
> 频道：papers | 更新日期：2026-10-07 | 标签：arxiv, cs.RO
> 核心摘要：RobotWorld在仿真中将指令和观测转为机器人接口执行，用84项任务评测多模态智能体能力与缺口。

# RobotWorld：面向多样任务与具身形态的机器人使用多模态智能体基准测试

::: v-pre
> 原文链接：[RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments](https://arxiv.org/abs/2610.10409)（arXiv 2610.10409 · 发布日期：2026-10-07）

**RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments**

RobotWorld在仿真中将指令和观测转为机器人接口执行，用84项任务评测多模态智能体能力与缺口。

## 核心要点

- 动机：检验会写代码、用工具的通用智能体能力能否迁移到物理世界。
- 方法：RobotWorld设置交互预算和可执行成功检查，分析任务结果与执行轨迹。
- 结果：智能体能构建感知控制流程，但常难以组合成可靠成功行为。
- 差异：Astra更常完成空间和受限接触目标，Opus 5.5更常完成平衡与定时交互目标。

**验证范围与局限**：验证范围为仿真测试床中的84项任务，涵盖操作、移动操作、运动、驾驶和空中控制。

## 英文摘要 (Abstract)

General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Its 84 tasks span manipulation, mobile manipulation, locomotion, driving, and aerial control, with explicit interaction budgets and executable success checks. By analysing task outcomes alongside execution traces, we identify both the capabilities that transfer and the gaps that prevent reliable completion. Furthermore, we find that current agents can construct sophisticated perception and control workflows, including image segmentation, camera calibration, spatial estimation, and dynamics-based computation. These capabilities, however, do not consistently compose into successful behaviour: agents lose task-relevant object states despite reaching commanded poses, fail to correct ineffective actions, recover too late, or mistake unfinished tasks for completion. This uneven transfer also differs across models: Astra succeeds more often on spatial and constrained-contact goals, whereas Opus 5.5 succeeds more often on continuous-balance and timed-interaction goals. By linking these outcomes to execution behaviour, RobotWorld provides both a rigorous proving ground and an empirical account of the remaining capability gaps, thereby establishing concrete targets for training and designing more reliable physical-world agents.

作者：Zhiqin Yang, Chenxin Li, Xiaomeng Hu, Yibin Liu, Weidong Huang, Jiankai Sun, Haitao Li, Zijian Wu, Yuzhi Huang, Fanding Huang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.10409：RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments](https://arxiv.org/abs/2610.10409)