I am Youwei Liu, an undergraduate at Central South University. I am currently a Research Assistant at The Hong Kong Polytechnic University (PolyU NLP Lab), focusing on long-horizon agent planning by integrating LLM agents, embodied agents, reinforcement learning, and world models. I collaborate with Jian Wang on agent. Thanks to him for his generous guidance and support.

📖 Education

  • CSU Sep 2023 – 2027 (expected)   Central South University — Changsha, China
    • Undergraduate Student
    • Major: Data Science Excellence Talent Program

💻 Research Experience

  • PolyU NLP Apr 2025 – Present   PolyU NLP Lab — Hong Kong, China
    • Research Assistant
    • Working on long-horizon agent planning by integrating LLM agents, embodied agents, reinforcement learning, and world models.
  • CUHK(SZ) KAUST Jul 2024   CUHK (Shenzhen) & KAUST — Shenzhen, China
    • Visiting Student
    • Supervised by Jinchao Xu; research on multi-scale feature transmission across token, embedding, and contextual layers in LLMs.

🔥 News

📝 Publications

arXiv 2026
ITP workflow

Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

Youwei Liu, Jian Wang, Hanlin Wang, Beichen Guo, Wenjie Li

arXiv     PDF     GitHub     🤗 Hugging Face
  • Unified framework for agent learning via lookahead imagination with a learned world model.
  • Adaptive lookahead trades off ultimate goal and task progress to choose imagination horizon dynamically.
  • Training-free and RL-trained variants; strong results on representative agent benchmarks.

🎖 Honors and Awards

  • Outstanding Paper (Oral) — “Shenzhen Cup” Math Modeling Challenge Aug 2024
  • First Prize, National Undergraduate Math Modeling Competition Sep 2024
  • First Prize, National Undergraduate Market Research Analysis (CP Cup) May 2024
  • Second Prize, CSU Mathematical Modeling Competition Jun 2024
  • National-Level, Innovation and Entrepreneurship Training Award Apr 2024
  • National Second Prize, Service Outsourcing Innovation and Entrepreneurship Competition May 2025
  • Honorable Mention, Mathematical Contest in Modeling (MCM), COMAP-USA Jan 2025