Macaron-A2UI:面向个人智能体的生成式UI模型
阅读原文· arxiv.org为突破个人智能体静态文本交互的瓶颈,生成式UI成为动态界面层的新方向。本文提出Macaron-A2UI模型,旨在使智能体能同时生成自然语言与轻量级、可执行的UI动作,用于信息收集、偏好优化、确认及多目标组织。研究构建了大规模生成式UI语料库,引入A2UI-Bench评测基准,并训练了30B、235B和754B参数规模的模型。最强的Macaron-A2UI模型在A2UI-Bench上获得75.6分,超越了全schema前沿基线。模型、基准与评测协议均已开源。
As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer, dynamically synthesizing the right controls, options, and state from the interaction context in real time. We present Macaron-A2UI, a model for Generative UI in personal agents. Our goal is to move beyond text-only interaction by enabling agents to generate natural language together with lightweight, executable UI actions for information collection, preference refinement, confirmation, and multi-goal organization. We build a large-scale Generative UI corpus from heterogeneous dialogue sources, introduce A2UI-Bench for controlled evaluation, and train 30B, 235B and 754B models with parameter-efficient LoRA-based supervised fine-tuning followed by reward-driven reinforcement learning. The best Macaron-A2UI model reaches 75.6 overall on A2UI-Bench without explicit schema hints, surpassing the strongest full-schema frontier baseline. We release the models, benchmark, and evaluation protocol to support future work on Generative UI for personal agents.