Evolving Agent Interfaces· 进化代理接口
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the knowledge of when to use each are built by hand, which cannot keep pace with new applications, workflows, and models. We argue that interface design should itself be an agent capability. We introduce Agent S4, an autonomous computer-use scientist that builds Evolving Agent Interfaces from task experience. A meta-agent examines task agents' trajectories on synthetic training tasks, without success labels, and constructs and revises interfaces and usage knowledge in a repository. Population-based evolution then selects which repositories
通过任务经验自主构建和进化代理接口。
- 核心方法
- 引入Agent S4，一个能从任务经验中构建和修订代理接口及使用知识的自主计算机科学家元代理，使用基于人群的进化算法选择最优的接口仓库。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有的代理接口和使用知识手动构建，难以适应新应用和工作流程的变化。
- 关键实验
- 未提供
- 主要贡献
- 提出了一种新的自动进化代理接口的方法，提高了代理在不同任务中的适应性和效率。
- 意义与局限
- 该方法有望加速代理技术的发展，减少手动设计接口的工作量，但尚未经过实验验证。