today local_bar

Yu Yao

Lecturer, University of Sydney

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Can Dependencies Induced by LLM-Agent Workflows Be Trusted?

#1904 · Yu Yao, Yiliao Song, Yian Xie, Mengdan Fan, Mingyu Guo, Tongliang Liu

This paper presents a dynamic framework that enables reliable execution under violated conditional independence assumptions.