Author

Rui-Qi He

h-index 1 View on Semantic Scholar

We have 2 of 8 papers

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

When Should a VLM Look? Paying Only for Visual Calls That Were Needed and Used

From the same cold start, prompt pool, and budget, CounterCredit reaches 89.5% on V*, 80.2% on HR-Bench-4K, and 76.4% on HR-Bench-8K, and raises the spurious-call rate to 31% to 36%, the lowest among the agents evaluated.

Kun-Yu Peng, Jun-Ming Liu, Rui-Qi He et al. · 0 citations

Jul 2026

Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories

These results show that benign execution trajectories can expose proprietary procedural knowledge, and SigLeak, a black-box framework that exploits recurring skill signatures in agent behavior, outperforms or matches three baselines in nearly every setting.

Jianing Geng, Ruiqi He, Zekun Fei et al. · arXiv.org · 3 citations