[论文解读] Software as Content: Dynamic Applications as the Human-Agent Interaction Layer

Mulong Xie, Yang Xie|arXiv (Cornell University)|Mar 22, 2026

Speech and dialogue systems被引用 0

一句话总结

本文提出 Software as Content (SaC)，其中动态生成的具代理性的应用程序作为人类与AI代理之间的持久、双向交互层，解决基于聊天的界面对结构化任务的局限性。

ABSTRACT

Chat-based natural language interfaces have emerged as the dominant paradigm for human-agent interaction, yet they fundamentally constrain engagement with structured information and complex tasks. We identify three inherent limitations: the mismatch between structured data and linear text, the high entropy of unconstrained natural language input, and the lack of persistent, evolving interaction state. We introduce Software as Content (SaC), a paradigm in which dynamically generated agentic applications serve as the primary medium of human-agent interaction. Rather than communicating through sequential text exchange, this medium renders task-specific interfaces that present structured information and expose actionable affordances through which users iteratively guide agent behavior without relying solely on language. These interfaces persist and evolve across interaction cycles, transforming from transient responses into a shared, stateful interaction layer that progressively converges toward personalized, task-specific software. We formalize SaC through a human-agent-environment interaction model, derive design principles for generating and evolving agentic applications, and present a system architecture that operationalizes the paradigm. We evaluate across representative tasks of selection, exploration, and execution, demonstrating technical viability and expressive range, while identifying boundary conditions under which natural language remains preferable. By reframing interfaces as dynamically generated software artifacts, SaC opens a new design space for human-AI interaction, positioning dynamic software as a concrete and tractable research object.

研究动机与目标

• 识别基于聊天的人类-代理界面的根本局限性（表示不匹配、交互熵、状态易逝）。
• 提出 SaC 作为一种范式，在该范式中动态生成的具代理性的应用程序充当主要交互媒介。
• 形式化 SaC 人类-代理-环境模型并描述代理应用的生命周期与设计空间。
• 开发系统架构并提供参考实现，以证明在不同任务领域的可行性。
• 推导将生成式界面与具代理执行相结合的设计原则，并在选择、探索和执行等任务中进行评估。

提出的方法

• 定义三层次的人类-代理-环境交互模型，并引入作为持久界面的具代理性应用。
• 描述用于增量改进、结构扩展和全界面重新配置的多层渲染策略。
• 以双通道模型 formalize SaC，结合结构化可供性与自然语言输入。
• 提供具代理应用意图、数据和时间演化模式的分类学。
• 提出参考系统架构与实现，以使 SaC 可落地。
• 通过场景驱动的评估，在选择、探索和执行任务上展示可行性与覆盖范围。

Figure 1 . Given the same user query, chat returns a continuously accumulating conversation wall (left); Software as Content generates an evolving agentic application that serves as a bidirectional interaction layer between human and agent (right).

实验结果

研究问题

• RQ1 哪些基于聊天的界面对复杂、结构化任务和不断演化的交互造成限制？
• RQ2 动态生成的具代理性应用如何有效实现双向的人类-代理交互？
• RQ3 在 SaC 范式下，具代理应用的生命周期、设计空间与分类学是什么？
• RQ4 哪些设计原则与架构能够实现具代理界面的持久性、演化性与个性化？

主要发现

• SaC 能够提供一个持久、不断发展的人机交互层，通过结构化的可用性与自然语言将人类与代理连接起来。
• 代理应用通过持续的交互循环趋向于个性化、任务特定的软件。
• 形成的人类-代理-环境模型与设计原则支配代理界面的生成与演化。
• 一个参考系统展示了 SaC 在选择、探索和执行等任务上的可行性。
• 作者识别出在自然语言仍比结构化界面更优的边界条件。

Figure 2 . Positioning and comparison of existing interaction paradigms along two dimensions: information complexity —the degree to which a task requires structured, organized information architecture rather than linear presentation; personalization —the degree to which the interaction medium adapts