About

I am a Ph.D. student in Computer Science at the University of Central Florida, advised by Prof. Song Wang. Before joining UCF, I earned my B.S. in Computer Science and Technology from the University of Science and Technology of China and studied at the University of Sydney as an exchange student.

My current research focuses on long-horizon LLM agents, including multi-agent collaboration and memory for long-term interaction. Previously, I worked on reliable LLM evaluation, including LLM-as-a-judge and multi-agent debate, and on multimodal benchmarking.

Selected Publications

• Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
  T. Hu, Z. Tan, S. Wang, H. Qu, and T. Chen · NeurIPS 2025 · Project page

• MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
  T. Hu, W. Lin, W. Zhang, J. Ma, and S. Wang · arXiv 2026 · Project page

• PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding
  Z. Huang, X. Liu, T. Hu, K. Zhang, and Y. Liu · arXiv 2025 · Project page

More Information

See my curriculum vitae for education, publications, and research and professional experience, or my Google Scholar profile for a full publication list.