Zongyu Wu

PhD student, The Pennsylvania State University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

#3405 · Fali Wang, Hui Liu, Zhenwei DAI, Jingying Zeng, Zhiwei Zhang, Zongyu Wu, Chen Luo, Zhen Li, Xianfeng Tang, Qi He, Suhang Wang

We introduce AgentTTS, an LLM-agent framework that efficiently allocates test-time compute across multi-stage tasks, achieving compute-optimal performance through insight-guided adaptive search.