Zurueck zur Liste
πŸ“„Papers

MAIC-UI: Making Interactive Courseware with Generative UI

Tu S. et al.
2026-04

Ueberblick

Recent arXiv paper introducing a zero-code GenUI system for educational courseware. MAIC-UI turns textbooks, PPTs, and PDFs into interactive learning pages, uses a generate-verify-optimize pipeline for pedagogical accuracy, and supports click-to-locate incremental edits instead of expensive full regeneration.

Zusammenfassung

Why This Paper Is Worth Adding:

1. Concrete domain system: Shows Generative UI applied to a real authoring workflow, not just generic chat interfaces
2. Interaction over static output: Targets interactive simulations and manipulable learning pages instead of slide-like HTML
3. Editability focus: Introduces click-to-locate incremental editing for much faster iteration cycles
4. Evidence beyond demos: Reports both a controlled lab study and a three-month classroom deployment
5. Collection fit: Strong example of GenUI moving into domain-specific production scenarios with measurable outcomes

Tags

educationcoursewaregenuiinteractive-learning

Aehnliche Artikel

πŸ“„Papers

Macaron-A2UI: A Model for Generative UI in Personal Agents

Fresh 2026 arXiv paper focused on runtime Generative UI for personal agents. The authors argue that plain chat becomes a bottleneck for complex agent tasks, introduce a large-scale Generative UI corpus plus A2UI-Bench, and train models that generate natural language together with lightweight executable UI actions for confirmation, preference refinement, and multi-goal coordination.

agentsa2uibenchmark
von Kong F. et al. Β· 2026-05
Mehr lesen
πŸ“„Papers

Efficient Personalization of Generative User Interfaces

Recent arXiv paper on one of the core unsolved GenUI problems: personalization. The authors collect pairwise judgments from trained designers over the same 600 generated UIs, show that design preferences diverge substantially, and propose a sample-efficient preference model that personalizes generated interfaces better than baseline evaluators and direct prompting.

personalizationgenuiarxiv
von Peng Y.-H. et al. Β· 2026-04
Mehr lesen
πŸ“„Papers

Software as Content: Dynamic Applications as the Human-Agent Interaction Layer

2026 arXiv paper arguing that chat alone is a poor medium for structured, stateful human-agent work. The authors propose Software as Content, where dynamically generated agentic applications become the primary interaction layer, persist across turns, and expose actionable controls instead of forcing everything through linear text.

agentic-appsgenuistateful-ui
von Xie M. and Xie Y. Β· 2026-03
Mehr lesen

Ein kuratiertes Verzeichnis fuer Generative UI, GenUI und sichere KI-Schnittstellen.

Erstellt mit ❀️ von der Community