العودة إلى القائمة
📄الأبحاث

TaskArtisan: Designing Composable Generative Widgets for LLM-Assisted Analysis

Chen M. and Pavel A.
2026-07

حول

July 2026 HCI paper examining how Generative UI can make long, multi-step chatbot analysis workflows easier to revisit and reuse. TaskArtisan lets people create analysis widgets and compose them into sequential or fan-out workflows, then compares the approach with a conventional chatbot in a 12-participant study.

الملخص

Why TaskArtisan Adds New Signal:

1. Composable generated UI: Treats generated widgets as reusable workflow building blocks rather than one-off responses
2. Analysis-specific design: Supports scripts, visualizations, and summaries across multi-step analytical work
3. Two composition modes: Covers both sequential pipelines and fan-out exploration
4. Evidence-backed trade-offs: Finds better clarity and visual presentation alongside rigidity and additional prompting costs
5. Practical framework: Organizes future designs around malleability, specification, and interoperability

الوسوم

generative-widgetsanalysiscompositionhuman-ai-interactionuser-study

مقالات ذات صلة

📄الأبحاث

ControlAnything: Generative UI and On-Demand Device Integration in Mixed Reality

November 2026 preprint generating both spatial controls and the connector code for physical devices when a Quest 3 wearer requests them. A coding agent tests connections over hand-written MIDI, Bluetooth, and key-press transports, then returns AR widgets, a per-frame hand program, or both.

generative-uimixed-realitydevice-integration
بواسطة Bektur Ryskeldiev · 2026-11-05
اقرأ المزيد
📄الأبحاث

Interface Quilt: Modifying Applications with Computer Use Agents and Generative UI

November 2026 preprint from Autodesk Research combining computer-use agents and GenUI to build persistent interface patches over existing applications. It recovers controls from rendered pixels, generates new interaction surfaces, and synchronizes them with the underlying app without requiring source code, APIs, or accessibility data.

generative-uicomputer-use-agentsinterface-patches
بواسطة Qiu L. et al. · 2026-11-01
اقرأ المزيد
📄الأبحاث

ABRA: Agent-Bound UI for Human-Agent Communication beyond Chat with Reusable Views

October 2026 EMNLP system demonstration separating reusable graph, table, text, and display views from task-specific interaction meanings. ABRA publishes these bindings as shared canvas state so users and other agents can inspect and invoke task-specific actions.

generative-uishared-canvasesinteraction-semantics
بواسطة Kim S. G. and Kim H. · 2026-10-22
اقرأ المزيد

مجموعة منتقاة من مصادر Generative UI وIntelligent UI وGenUI وواجهات AI الديناميكية.

صُنع باستخدام ❤️ من قِبل المجتمع