In-Context Robot Learning with VLM Agents

  • 类型：arxiv
  • 标识：2609.19138
  • 链接：https://arxiv.org/abs/2609.19138
  • 主分类：agent
  • 形态：application
  • TLDR：Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feed
  • 副分类：multimodal
  • 待LLM分类：否
  • 标题中文：基于 VLM Agent 的机器人上下文学习
  • TLDR中文：让机器人像人类一样轻松地适应陌生环境仍是具身 AI 的远景目标。任何有限规模的演示都无法覆盖机器人将遇到的所有任务与场景，使得从部署时上下文学习的能力对泛化至关重要。然而，此类上下文学习（ICL）在很大程度上仍超出现有机器人策略的能力范围。商用 vision-language models（VLM）（如 GPT-6 Astra）所具备的广泛 Agentic 能力引出一个关键问题：这些模型能否从演示、示例与交互反馈中进行学习...
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-17-agent-rag-longcontext-candidates.json