Skip to content
Source
Agent Control Flash News·· 3h agoAI Score55

真·混合 GUI+CLI 环境缺货:上交/浙大 CUA-Universe,OSWorld SR +16.8

真·混合 GUI+CLI 环境缺货:上交/浙大 CUA-Universe,OSWorld SR +16.8

Edge-TTS Studio Audio
Free for all listeners
Click to synthesize audio
00:00
00:00
AI Overview

View PDF HTML (experimental) Abstract: Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combining visual-state inspection with...

Primary Source
Academic Paper·arXiv:2609.05374

CUA-Universe (arXiv:2609.05374)

“View PDF HTML (experimental) Abstract: Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly t”

Body

View PDF HTML (experimental)

Abstract:Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combining visual-state inspection with precise, high-throughput command-line operations, so capable agents must coordinate both modalities over shared application state. Yet scalable hybrid environments remain scarce because supporting both GUI and CLI over real applications typically requires substantial manual engineering for each application. Existing agents also struggle to use the two interfaces complementarily: CLI-native agents lack visual perception for tasks involving interface state or layout, while GUI-native agents are inefficient for operations better executed through commands. We introduce CUA-Universe, a scalable environment-to-data pipeline that turns real desktop software into hybrid GUI+CLI environments. App-Forge adapts applications into reproducible VMs and command-line surfaces it discovers, wraps, or generates, scaling to 16 applications; Task-Weave synthesizes diverse hybrid tasks of controllable difficulty from reusable operations over seed files; and Path-Steer steers rollouts along efficient hybrid paths and harvests verified trajectories for post-training. Training on this data shifts behavior from inefficient GUI interaction and brittle CLI scripting toward effective GUI+CLI orchestration. Our 9B model improves both success and efficiency on CUA-Verse (Score +39.3 pts; -37% steps, -60% tokens), OSWorld (SR +16.8 pts; -57% steps, -44% tokens), and OSWorld-MCP (Score +7.84 pts; -27% steps, -30% tokens). CUA-Universe provides a scalable path toward more capable and efficient computer-use agents.
Comments: 21 pages, 9 figures
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2609.05374 [cs.AI]
  (or arXiv:2609.05374v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2609.05374

arXiv-issued DOI via DataCite

Submission history

From: Haoting Shi [view email]
[v1] Fri, 4 Sep 2026 17:26:18 UTC (16,281 KB)

Source: Agent Control Flash News · arxiv.org

Related Products & Analysis

Original·站长/Quantara 团队·~3 min read

Cursor Agent 架构全景拆解:从影子工作区到多文件推演引擎

全面剖析 Cursor 在 Agent 模式下的底层技术实现,解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。

Underlying architectures & industry dynamicsRead Analysis →
Curated·Vercel Changelog·~1 min read

Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览

动态速评:v0 正在从单一组件生成器演进为全栈应用搭建协作台,尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。

Underlying architectures & industry dynamicsRead Analysis →