Yule Wen

2 accepted papers

2026

Contextualized Privacy Defense for LLM Agents

Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi, Xing Xie, Diyi Yang

ICML 2026poster

LLM agents increasingly act on users’ personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These paradigms are insufficient for supporting contextual, proactive pr…

Cited by 0 Source ↗Scholar ↗

2026

Real-Time Reasoning Agents in Evolving Environments

Yule Wen, Yixin Ye, Yanzhe Zhang, Diyi Yang, Hao Zhu

ICLR 2026poster

Agents in the real world must make not only logical but also *timely* judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still unfolding. Despite advances in language model reasoning, exi…

Cited by 0 Source ↗code ↗Scholar ↗