English(EN) Vision-Language Agents Can Learn in Their Own Latent Worlds

新的Dwell框架使视觉-语言智能体能够在潜在世界中学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员推出了一种新颖的基于模型的强化学习框架Dwell，该框架利用预训练的视觉-语言模型（VLMs）作为循环潜在状态转移算子。这种方法使智能体能够利用VLMs的内部表征进行策略改进，在其自身的潜在世界中进行学习和适应。Dwell在各种交互式视觉环境中取得了出色的性能，同时显著降低了与想象相关的计算成本，证明了VLMs智能体的有效世界模型需要预测有用的动作而不是重建未来。 AI

影响该框架可以通过利用VLMs在潜在空间中进行持续学习和预测，从而实现更高效、更具适应性的AI智能体。

排序理由该条目是一篇学术论文，详细介绍了一种新的AI智能体框架和方法论。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇学术论文，详细介绍了一种新的AI智能体框架和方法论。[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: paper, model release; 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]

arXiv cs.AI TIER_1 English(EN) · Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo · 2026-10-28 04:00

视觉-语言代理可以在其自身的潜在世界中学习

arXiv:2610.36925v1 Announce Type: new Abstract: Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) already internalize rich world knowledge, yet this knowledge is ra…

本文如何被排名

报道来源 [1]

视觉-语言代理可以在其自身的潜在世界中学习

相关实体

相关话题