arxiv arXiv cs.LG · 1h ago · research

Qwen releases Qwen-CUA, a 397B-A17B native computer-use agent

from English

Qwen introduces Qwen-CUA, a native computer-use agent built on a 397B-A17B mixture-of-experts backbone that operates via screenshots and input events without relying on DOM trees or accessibility metadata. The system utilizes a scaffold to maintain up to 20 active screenshots and was trained using a cloud rollout fleet with nearly 100,000 vCPUs across approximately 40,000 verifiable tasks.

Qwen-CUA outperforms Qwen3.7 on eight benchmarks, achieving 86.2 on OSWorld-Verified and competitive scores on OSWorld 2.0.
Scaling the approach to over one trillion parameters yields Qwen-CUA-Max, which improves OSWorld-Verified scores to 87.6.
The model reduces RedTeamCUA attack success rates from 36.6 to 16.4 relative to Qwen3.7.

These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction as a key direction for future development.

Importance 2/3 arXiv cs.LG Alibaba (Qwen) AI agents Research paper

Benchmarks

Benchmark	Model	Score
OSWorld 2.0	Qwen-CUA-Max	21.2%
OSWorld 2.0	Qwen-CUA	18.5%

Read original

arxiv arXiv cs.CL · 5h ago · 2 views

Qwen releases Qwen-CUA, a 397B-A17B native computer-use agent

Researchers have introduced Qwen-CUA, a native computer-use agent built on a 397B-A17B Qwen mixture-of-experts backbone. The system operates by observing screenshots and acting through keyboard and mouse events, without relying on DOM trees or accessibility metadata.

arxiv arXiv cs.AI · 4d ago · 1 view

Qwen-UI-Agent sets state of the art on mobile-use benchmarks

The Qwen team has released a technical report for Qwen-UI-Agent, a real-world centric foundation GUI agent designed to operate reliably across mobile, computer-use, web, and DeepSearch environments. The system combines diverse sandbox environments with a large-scale real-device mobile runtime, interleaving GUI operations with CLI execution and supporting long-horizon tasks.

arxiv arXiv cs.CL · 7d ago

AgentOmnia scales agentic models across full-scenario applications

Researchers present AgentOmnia, a framework for full-scenario agentic scaling that coordinates task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer, To-Business, and To-Employee applications. The system utilizes an extensible taxonomy and constructs 5,018 stateful environments with 255,375 tools and 52,361 tasks to enable fine-grained diagnosis via OmniaBench.

arxiv arXiv cs.LG · 19d ago

TRACE improves long-horizon agent tool-use via turn-level credit estimation

The authors propose TRACE (Turn-level Reward Assignment via Credit Estimation), a dense credit-assignment method for agentic reinforcement learning that addresses the sparsity and high variance of outcome rewards in long-horizon tasks. By representing rollouts as state transitions at tool-call boundaries and deriving per-action rewards from log-ratio state values, TRACE enables effective training without additional critics or supervised fine-tuning stages.

arxiv arXiv cs.AI · 41d ago · 1 view

Hypothesis-Driven Skill Optimization for LLM Agents

HDSO enables safe, auditable skill updates for LLM agents without training, using falsifiable hypotheses and validation. On ALFWorld, it improves Qwen3-8B by +6.9 Avg. SR points and maintains a +7.1-point gain under noisy feedback, with validated skills transferable across runs and models when diagnostic alignment is achieved.