[论文] The Power of Meta Access in the Software of the Future --- Demonstrate...

论文概要

研究领域: AI
作者: Julian Kunkel, Ali Doosthosseini
发布时间: 2026-11-05
arXiv: 2611.08428

中文摘要

尽管像 OpenCode 这样的 Agent 工具在编码和自动化方面表现出色，聊天仍然是许多大语言模型（LLM）任务的默认交互界面。然而，模型只能看到当前对话，看不到周围的工作空间。我们探索了「元访问」（meta access）——赋予助手一个结构化的、有权限约束的界面自身视图——并提出了层级阶梯：功能教学；元数据、设置和偏好访问；摘要和消息检索；确认式变更；以及完全编排。元访问可以将聊天客户端从多屏操作转变为查找、导航、组织和操作的单入口，但同时带来关于事实锚定、隐私、提示注入和信任的风险。通用 Agent 运行时是运行环境；因为它们可以更改自己的设置，元访问变成了自反的，需要一个独立的控制面边界。我们在 Chat AI 客户端的 Meta Chat 原型中落地了这一理念。它从摘要、设置和相关消息构建有界上下文；将引用链接到对话、主题和人格；支持确认的、可逆的变更；提供可浏览的教学库；并推荐人格作为用户发起的对话。通过以结构化形式暴露应用状态，元访问可以将屏幕阅读器从控件描述扩展到语义工作空间操作。元访问因此将聊天从单对话的窗口转变为整个工作空间的控制层，在不让渡用户控制的前提下将聊天延伸到 Agent 能力。随着助手嵌入 IDE、仪表盘、办公套件和操作系统，AI 时代的界面应该暴露一个结构化的、有权限的自身状态和能力模型，最理想的方式是通过调试器式界面开放其已有的元模型。

原文摘要

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.

自动采集于 2026-11-08

#论文 #arXiv #AI #小凯