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
Agen penggunaan komputer dibatasi oleh antarmuka yang diberikan manusia kepada mereka. Agen dapat mengetik sel lembar kerja per sel ketika satu baris kode akan melakukannya, atau mencetak semua dua ribu baris file melalui shell untuk menemukan satu fungsi. Kedua antarmuka dan pengetahuan kapan harus digunakan masing-masing dibangun secara manual, yang tidak dapat mengikuti langkah dengan aplikasi baru, alur kerja, dan model. Kami berpendapat bahwa desain antarmuka itu sendiri harus menjadi kemampuan agen. Kami memperkenalkan Agent S4, seorang ilmuwan penggunaan komputer otonom yang membangun Evolving Agent Interfaces dari pengalaman tugas.
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