Elamur Research⌕
☰
home / authors / Zhengxi Lu

Zhengxi Lu

Zhengxi Lu has 4 papers in our library, in 2026, most of them on Evaluation & benchmarks; often with Guangyi Liu, Fei Tang, Hao Wang.

4 papers in our library · 2026

OpenAlex · h-index 1 · 3 works · 1 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 15 times in our library · ⭐ Paper Stars ranking: #9327

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 9The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArts and Humanities · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksHuman-Computer Interaction · 2 worksInformation Systems · 2 worksEngineering · 1 workIndustrial and Manufacturing Engineering · 1 workSoftware · 1 work

🧭 Topics 1Research subjects and languages the work is about.Evaluation & benchmarks · 2 works

 Works by year

2020s

20264 papers

 Papers

The most cited first (OpenAlex and our library).

  1. LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark (2026 · 9 citations)
    Mobile GUI agents built on large language models often fail in rare, app-specific situations that pre-training or fine-tuning cannot fully cover.
  2. MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents (2026 · 6 citations)
    Mobile agents driven by multimodal LLMs usually act only through the interface: they tap, swipe and type step by step. This is flexible but slow. Shortcuts such as APIs, deep-links and RPA scripts can skip whole sequences of GUI steps, but no benchmark has systematically tested agents that mix the two.
  3. UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026 · 1 citation)
    Multimodal GUI agents perform well on short mobile tasks but break down on long, memory-heavy ones. Existing 7B models lose about 90.9% of their accuracy on MemGUI-Bench. The authors trace these failures to three causes: forgetting earlier observations, losing track of task progress, and making arithmetic mistakes.
  4. Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026)
    Training vision-based GUI agents for long, multi-step tasks involves a trade-off. Single-turn RL methods such as GRPO learn from expert histories, but at deployment the agent must rely on its own past actions, so training and real use differ. Online multi-turn RL closes this gap, but it brings sparse rewards, high…

 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 15 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhengxi-lu/