Author

Zihan Dong

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design

Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, structured artifacts. Mechanical computer-aided design (CAD) is a particularly demanding setting: an agent must manipulat...

Zi-Han Dong, Yuan-Zhe Liu, Zhi-Yuan Ma et al. · 0 citations

Jul 2026

Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees

Results suggest that AAPT performs best when candidate actions can be enumerated in advance, whereas reactive execution remains stronger when they cannot, and on an external benchmark, AAPT matches the overall performance of a reactive baseline, although the two methods exhibit complementary strengths.

Zi-Han Dong, Rui Qian, Ruifang Qian et al. · arXiv.org · 0 citations