Tong Zhang, Yuxuan Cheng, Ruimin Zhang, Yun Peng, Tao Xie · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27977 · cited by 0 works (OpenAlex) · open-access PDF
एप्लिकेशन दैनिक कार्यों को पूरा करने के लिए उपयोगकर्ताओं के लिए सुविधाजनक सुविधाएं प्रदान करते हैं। हालांकि, अलग-अलग उपयोगकर्ताओं को एक ही एप्लिकेशन के लिए अलग-अलग या यहां तक कि विरोधाभासी आवश्यकताएं हो सकती हैं, जबकि एक ही उपयोगकर्ता की आवश्यकताएं समय के साथ बदल सकती हैं। एजेंट-टू-एप्लिकेशन या यूआई-टू-कोड दृष्टिकोण द्वारा उत्पादित अनुप्रयोगों को अनुकूलित करने के लिए उत्पन्न कार्यान्वयन में बदलाव की आवश्यकता हो सकती है। हम एजेंट के रूप में एप्लिकेशन, एक कार्य की पेशकश करते हैं जिसमें उपयोगकर्ता प्राकृतिक भाषा में अपनी आवश्यकताओं को व्यक्त करते हैं और एजेंट उपयोग के दौरान अपने व्यवहार को प्रदान करने के लिए एक व्यक्तिगत अनुप्रयोग बनाता है। हम LiveUIAgent को
Machine translation (Meta M2M100); the English original follows.
Applications provide convenient features for users to complete daily tasks. However, different users may have different or even conflicting requirements for the same application, while the requirements of the same user may change over time. Personalizing applications produced by agent-to-app or UI-to-code approaches can require changes to the generated implementation. We propose Agent as App, a task in which users express their requirements in natural language and an agent creates a personalized application while continuing to supply its behavior during use. We implement LiveUIAgent, which generates a task-specific orchestration connecting the user interface, saved information, and service actions. A shared agent runtime renders and updates the interface while carrying out the requested operations. Revising the orchestration and interface while reusing that runtime provides a lightweight basis for personalization as requirements evolve. We introduce LiveUIBench, a benchmark with diverse requirements and ordered interactions across personal services. The empirical findings show that the evaluated models struggle to complete these workflows reliably. Applications can satisfy many local checks while leaving the overall task unfinished, and greater partial coverage can coincide with fewer completed workflows.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Orchestration, Workflow, Personalization, Task (project management), Reuse
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27977, 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