arxiv arXiv cs.AI · 1h ago · research

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

from English

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.

Achieves 82.1% on MobileWorld, 92.2% on MobileWorld-Real, and 97.5% on AndroidDaily benchmarks.
Reaches 79.5% on OSWorld-Verified and a 40.0% partial-progress score on OSWorld-v2 for computer use.
Scores 73.6% on WebArena and 81.5% on ScreenSpot-Pro for browser use and GUI grounding.
Utilizes an AutoResearch-style data flywheel and online RL with over 10,000 concurrent environments.

Qwen-UI-Agent sets state-of-the-art performance on mobile-use benchmarks while delivering competitive results against frontier models like Opus 4.8, Gemini 3.1 Pro, and GPT-5.6 Sol.

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

Benchmarks

Benchmark	Model	Score
WebArena	Qwen-UI-Agent	73.6%

Read original

arxiv arXiv cs.CL · 3d 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 · 14d 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 · 36d 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.

arxiv arXiv cs.CL · 37d ago · 6 views

Qwen-AgentWorld: Language World Models for General Agents

Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B are the first language world models that simulate agentic environments across seven domains using long chain-of-thought reasoning. Trained via a three-stage pipeline—CPT, SFT, and RL—these models outperform existing frontier models on AgentWorldBench, a benchmark derived from real-world interactions of five models on nine established tasks.

arxiv arXiv cs.AI · 37d ago · 2 views

Social World Model for Lifelong Social Intelligence

The Social World Model decomposes social interaction into five dimensions to enable closed-loop learning. It allows open-source models to sustainably improve and retain social capabilities, outperforming baselines and matching closed-source Gemini 3 Flash in key metrics without forgetting across difficulty levels.