Research profile

Experience timeline

Apr 2026 - Present Research Intern Alibaba · Qwen Agent Post-Training Group
2025 - Present PhD Student Shanghai Jiao Tong University · X-LANCE Lab
Mar 2025 - Aug 2025 Research Intern Beijing Institute for General Artificial Intelligence (BIGAI)
2021 - 2025 B.Eng. in Computer Science Shanghai Jiao Tong University

Solve intelligence, and then use it to solve everything else!

Rui Xie PhD Student in Computer Science · Shanghai Jiao Tong University

I am a PhD student in Computer Science at Shanghai Jiao Tong University, working toward generally capable agents that can take on work across software, devices, and everyday environments.

I care about agent systems that can complete real work, from computer operation to broader everyday tasks, with an emphasis on grounded interaction, reliable training pipelines, and evaluation in real settings.

Since April 2026, I have been interning with Alibaba's Qwen team, participating in post-training for Qwen mainline foundation models and improving agent capabilities for computer-use domains.

Research Directions: GUI agentsLLM agentsAgentic RLAGI

Email Download CV GitHub Google Scholar

Selected publications

Recent papers and ongoing research threads.

View all publications

Findings of EMNLP 2026

ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions

First Author 2026

An agent-native interface that replaces screenshot-and-click control with structured software state and code-executable semantic actions, reaching 81.6 on GPT-5.4 under a 15-action budget versus 6.6 for screenshot GUI control under 50 steps.

Rui Xie, Lu Chen

Project Page Paper Code Models Benchmark Training Data

arXiv Technical Report, 2026

Qwen-CUA: Native Computer Use for (almost) Everything

Core Contributor 2026

A technical report presenting a native computer-use agent that operates software from screenshots through keyboard and mouse actions, supported by large-scale verifiable tasks and interactive rollouts.

Qwen Team & XLang Lab

arXiv

ECCV 2026

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

First Author 2026

A training-free, plug-and-play framework that retrieves task-relevant tutorial videos and distills transferable planning and grounding knowledge for domain-specific GUI agents, yielding +4.47 to +7.48 point gains on OSWorld without modifying agent parameters.

Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li

arXiv Code Dataset

Under Review

MatToolBench: A Real-Environment Benchmark for Evaluating Multimodal Agents on Professional Materials Science Software

Co-first Author 2026

A real-environment benchmark that evaluates multimodal agents on professional materials science workflows spanning GUI tools, code execution, and cross-tool coordination.

Mei Wu, Rui Xie, Runyu Zhang, Lu Chen, Bo Chen, Kai Yu, Xin Chen

Featured projects

Flagship work on agents, evaluation, and real-environment systems.

Browse all projects

May 2026 - Present First Author

ASIL

An agent-native interface for software-operating agents that replaces screenshot-and-click control with structured state and semantic actions.

GUI AgentsSoftware InteractionAgentic RLBenchmarking

Open project page

Mar 2025 - Present First Author

GUIDE

A plug-and-play framework for reducing planning and grounding bias in domain-specific GUI agents by retrieving and distilling task-relevant tutorial knowledge.

GUI AgentsRetrieval-Augmented SystemsGroundingPlanning

Open project page

Oct 2025 - Present Co-first Author

MatToolBench

A real-environment benchmark for multimodal agents working with professional materials science software, covering GUI operation, code execution, and cross-tool workflows.

BenchmarkingReal-Environment EvaluationScientific SoftwareAgent Infrastructure

Open project page

Research timeline

From systems foundations to multimodal agent research.

Apr 2026 - Present

Research Intern

Alibaba · Qwen Agent Post-Training Group

Participating in post-training for Qwen mainline foundation models, with a focus on improving agent capabilities for computer use.

2025 - Present

PhD Student

Shanghai Jiao Tong University · X-LANCE Lab

Researching multimodal agents with an emphasis on GUI interaction, domain adaptation, and real-environment evaluation.

Mar 2025 - Aug 2025

Research Intern

Beijing Institute for General Artificial Intelligence (BIGAI)

Worked on multi-app macOS agents and early GUI-agent reinforcement learning pipelines, including desktop automation, task generation, and DAPO-based training adaptation.

2024 - 2025

Research Collaborator

Shanghai Jiao Tong University / BIGAI

Contributed to large-scale trajectory data construction and mobile GUI evaluation benchmarks.

2021 - 2025

B.Eng. in Computer Science

Shanghai Jiao Tong University

Built a strong foundation in systems, algorithms, architecture, and machine learning while moving into agent research.

CV and contact

Available for research conversations, collaborations, and project discussions.

The easiest way to reach me is by email. My current CV is available as a direct download, and this site will continue to grow as a durable record of publications, systems work, and research notes.

Email Download CV GitHub Google Scholar