论文多源确认

RoboTeam 基准:多机械臂视觉实时协同控制测试

RoboTeam: Benchmarking Vision-Based Multi-Agent Control of Many Robot Arms in Real Time

精选理由

多机械臂协作的新基准,只靠摄像头画面实时干活,不暂停世界也不给坐标。gpt-6.1-sol 能过 28 个任务但单任务要 3.5 小时和 2 亿 token,做机器人智能体和 agent 架构选型的人应该看看这套对比数据。

arXiv 发布 RoboTeam,一个模拟环境基准,要求智能体仅凭摄像头图像实时控制 4 到 16 台机械臂,包含 36 个需要协作的长时任务,如传递木料、用数百个方块拼图。与既有基准不同,它不提供物体真实坐标,且世界运行不暂停。

正文

论文以自适应系统为起点:由单个智能体决定何时分叉子智能体。该架构下 gpt-6.1-sol 和 opus-5.5 分别完成 28 和 27 个任务,其余四个模型最多完成 3 个。但代价高昂:gpt-6.1-sol 完成一个典型任务需 3.5 小时、2.18 亿输入 token,且约三分之一步骤至少失败重试一次。

论文随后对比三种固定架构:单智能体、层级式与去中心化。四者完成任务数接近,但层级式与去中心化更快、token 消耗最高 1.9 倍,单智能体省 token 但耗时 1.6 倍,自适应系统居中。结论是没有一种模型或架构能同时做到快、省、可靠,RoboTeam 正是用长时多臂任务、纯视觉输入和实时世界来暴露这些限制。

原文 · arXiv cs.AI

RoboTeam: Benchmarking Vision-Based Multi-Agent Control of Many Robot Arms in Real Time

Multimodal agents can now control robot arms by calling tools and writing code. Existing benchmarks fall short in three ways: most test one or two arms on short tasks, many pause the world while the agent thinks, and many give it ground-truth object positions. We present RoboTeam, a simulated benchmark where agents control 4 to 16 robot arms in real time from camera images alone. Its 36 tasks are long jobs that the arms must do together, such as passing timbers or building a picture from hundreds of cubes. We start from the most flexible agent system, the adaptive system, where one agent decides when to fork delegates. With it, gpt-6.1-sol and opus-5.5 complete 28 and 27 tasks, and four other models at most 3. But at a high price: a typical task takes gpt-6.1-sol 3.5 hours and 218 million input tokens, and a third of its steps fail at least once and must be retried. We then compare it with three fixed systems: single-agent, hierarchical, and decentralized. All four complete a similar number of tasks but differ in time and tokens. The hierarchical and decentralized systems are faster but use up to 1.9 times the tokens, and the single agent uses fewer tokens but takes 1.6 times as long, so the adaptive system lies between them. Even so, no model or system is yet fast, cheap, and reliable at once. RoboTeam measures these limits where earlier benchmarks cannot: long multi-arm jobs, camera images only, and a world that never pauses.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:RoboTeam、gpt-6.1-sol、opus-5.5、智能体,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Changxuan Fan, Zhongwei Xie, Boyi Zhang, Shaoli Hu, Chang Xu, Xiyu Ren, Yufei Li, Qiao Xiao, Huihao Jing, Kawai Chung, Wenbin Hu, Hongyu Luo, Lingyun Xie, Yisen Gao, Chunyang Li, Haoyu Huang, Wuganjing Song, Yuxuan Liu, Chiu Yeung Tang, Fangneng Zhan, Xi Yang),经 AITOP 多维评分管线结构化提炼。截至目前,全网已有 3 家独立信源对该事件进行交叉印证与跟进报道(含 Aravind Srinivas、Browser Use 等),属于近期高关注度行业信号。