Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega, Bhuvan Chandra Koduru, Chih-Lun Li, Jiachen Yang, Ang Li, Xin Eric Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28601 · open-access PDF
计算机使用的代理被人类给他们的界面所限制,代理可以单一代码行时按单元格键入表单单元格,或者通过壳打印文件的两千行以找到一个函数。接口和使用时的知识都是手工构建的,无法跟上新应用程序、工作流程和模型。我们认为界面设计本身应该是代理的能力。我们介绍了代理S4,一个自主的计算机使用科学家,从任务经验中构建进化代理界面。
Machine translation (Meta M2M100); the English original follows.
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'
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28601, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange