PulseAugur
中
实时 06:56:40
English(EN) Training Reasoning Models in Simulation to Natively Use Real Robots

在模拟中训练的开放权重模型可实现原生机器人控制

研究人员开发了一种方法,通过完全在模拟中使用强化学习来训练开放权重推理模型,以控制真实机器人。这种方法被称为机器人使用强化学习(RURL),它模仿了 GPT-6 Astra 和 Claude Fable 5.2 等专有模型获取计算机使用能力的方式。训练好的模型在现实世界的机器人任务中表现出很高的成功率,优于在演示数据上微调的模型,并保留了通用推理能力。 AI

影响 这项研究可能为现实世界的机器人应用提供更强大、更易于访问的开放权重模型。

排序理由 该项目是一篇研究论文,详细介绍了一种新的 AI 模型训练方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

在模拟中训练的开放权重模型可实现原生机器人控制

本文如何被排名

Signal score
37 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目是一篇研究论文,详细介绍了一种新的 AI 模型训练方法。[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
model release, product, 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]

  1. arXiv cs.LG TIER_1 English(EN) · Jiaming Tang, Zhuoyang Zhang, Junxian Guo, Fangzhou Zhao, Yilong Zhao, Zekai Li, Xingyang Li, Yuyang Zhao, Song Bian, Zhijian Liu, Song Han ·

    在模拟中训练推理模型以原生使用真实机器人

    arXiv:2611.18562v1 Announce Type: cross Abstract: Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, wher…