Biography

I am currently a tenure-track Associate Professor at the John Hopcroft Center and the APEX Data & Knowledge Management Lab of Shanghai Jiao Tong University. From September 2020 to April 2025, I worked at Huawei Noah’s Ark Lab. I received my Ph.D. in Computer Science and Engineering from The Chinese University of Hong Kong in 2020, supervised by Prof. Pheng Ann Heng and Prof. Shengyu Zhang. Before that, I received my bachelor’s degree in Computer Science and Technology from South China University of Technology in 2016.

I received the Best Paper Award at DLP-RecSys 2023 and the SJTU Top Ten Vertical-Domain Large Language Models Award in 2026. Our ToolACE series model ranks 1st among 8B-scale models on the Berkeley Function Calling Leaderboard, with over 700k total downloads.

My research focuses on building reliable, personalized, and proactive AI agents for real-world environments. I am particularly interested in large language model agents that can use tools, maintain long-term memory, and continuously learn from experience. If you would like to discuss potential collaboration or shared research interests, please feel free to contact me at wwliu(AT)sjtu.edu.cn.

Currently, our group works on the following research directions:

LLM Agents and Tool Intelligence: We study how LLMs interact with tools, APIs, software systems, search engines, databases, and real-world environments, aiming to build agents that can reason, act, and solve tasks through grounded tool use.
Proactive Agents: We develop agents that move beyond reactive responses by anticipating user needs, leveraging idle-time computation, preparing useful information in advance, and offering timely assistance.
LLM-Powered Recommendation and Personalized Agents: We build LLM-powered recommender systems and personalized agents that understand user preferences, reason over context, use tools, and support real-world decision-making.
Agent OS and Scalable Agent Infrastructure: We study infrastructure for large-scale agent systems, including parallel scheduling, context and memory management, tool/resource allocation, workflow orchestration, and efficient long-horizon execution.

Please note: If you do not receive a reply to your inquiry email, it may simply indicate that the opportunity is not the best fit at this time.

Recent Invited Talks

[May 2026] Invited talk at VALSE 2026 Tutorial 1: 智能体AI: “智能体大规模轨迹数据构建及微调”
[Apr 2026] Keynote at ICLR 2026 MemAgents Workshop: “Toward the Next Generation of Personalized, Proactive, and Self-Evolving Agents”
[Feb 2026] Invited talk at CCF Beautiful Lake Seminars (BLS, 秀湖会议): “个性化AI：从意图理解到自主智能体”

Weiwen Liu

Biography

Recent Invited Talks

Recent News