导读
metadata, settings, and preference access;links references to conversations, topics, and personas;supports confirmed, reversible changes;
【编辑部】这对你意味着什么
这条内容是一篇关于大语言模型聊天界面设计的 arXiv 论文摘要，讨论的是让助手以结构化、有权限的方式访问界面本身。它不涉及签证与移民、就业、收入与物价、教育或家庭生活等具体政策或生活事项，因此对在美华人读者的实际生活没有可直接说明的影响。
英文标题：The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI
arXiv编号：2611.08428
作者：Julian Kunkel, Ali Doosthosseini
来源：arXiv
原文链接：https://arxiv.org/abs/2611.08428
中文摘要：
Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface itself and propose a ladder of levels: feature tutoring; metadata, settings, and preference access; retrieval over summaries and messages, confirmed mutation, and full orchestration. Meta access can turn a chat client from many screens into one entry point for finding, navigating, organising, and operating it, while raising risks around grounding, privacy, prompt injection, and trust. General-purpose agentic harnesses are runtimes; because they can change their own settings, meta access becomes reflexive and needs a separate control-plane boundary. We ground this in the Meta Chat prototype of the Chat AI client. It builds bounded context from, e.g., summaries, settings, and relevant messages; links references to conversations, topics, and personas; supports confirmed, reversible changes; offers a browsable tutorial library; and recommends personas as user-started conversations. By exposing application state in structured form, meta access can extend screen readers from widget descriptions to semantic workspace operations. Meta access thus turns chat from a window onto one conversation into a control layer for the whole workspace, extending chat toward agentic capability without surrendering user control. As assistants become embedded in IDEs, dashboards, office suites, and operating systems, AI-era interfaces should expose a structured, permissioned model of their state and capabilities, ideally by opening their existing metamodels through a debugger-like interface.
本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。
【编辑部】今日讨论
你平时用聊天式 AI 工具时，更希望它能直接读取你当前的设置、历史对话和工作区来帮你操作，还是更希望它只停留在当前这段对话里？可以说说你自己的使用习惯或顾虑。
