Thanks to visit codestin.com
Credit goes to wanghanlinhenry.github.io

Hanlin Wang (王汉林) PhD Student Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China Email: hanlin-henry.wang (at) connect.polyu.hk   or                hlwang1024 (at) gmail.com Github   |   Google Scholar   |   Twitter

Hi! I am a PhD student at The Hong Kong Polytechnic University and a member of PolyU NLP Group, advised by Prof. Maggie Wenjie Li. Prior to that, I received my BEng degrees from Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, where I was honored to work with Prof. Ziqian Zeng.

News

[May 2026] 🔥 Got one paper (Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents) accepted by ACL 2026!.
[April 2025] 🔥 Got one paper (STeCa) accepted by ACL 2025!.
[Aug 2024] 🔥 Got one paper (E2CL) accepted by EMNLP 2024!.

Research

My research interests span Natural Language Processing (NLP) and Embodied AI, with particular focus on the following areas:

• LLM agents. My research focuses on developing autonomous agents with sophisticated reasoning capabilities through self-improvement mechanisms and emergent behaviors.
• Reinforcement Learning. I investigate novel RL algorithms and frameworks to optimize LLMs' decision-making processes and enhance their cognitive abilities in complex environments.
• Embodied AI. I explore methodologies for developing embodied agents capable of continuous learning and adaptation through multi-modal interaction and experience accumulation.

😀 I am open to collaborations and discussions. Please feel free to reach out to me if you are interested in my research or any relevant topics.

Selected Publications

(see full list in Google Scholar)

• Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents

  Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li
  Findings of ACL 2026. arXiv:2604.17252, 2026.
  [arXiv]

• Steca: Step-level trajectory calibration for llm agent learning

  Hanlin Wang, Jian Wang, Chak Tou Leong, Wenjie Li
  Findings of ACL 2025. arXiv:2502.14276, 2025.
  [arXiv]

• E2CL: Exploration-based Error Correction Learning for Embodied Agents

  Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li
  Findings of EMNLP 2024. arXiv:2409.03256, 2024.
  [arXiv]

• Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration

  Y Chen, Y Sun, H Wang, X Zhang, X Shen, W Li, W Zhang
  arXiv preprint arXiv:2603.06859, 2026.
  [arXiv]

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

  Y Liu, J Wang, H Wang, B Guo, W Li
  arXiv preprint arXiv:2601.08955, 2026.
  [arXiv]

• No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

  Chak Tou Leong, Yi Cheng, Kaishuai Xu, Jian Wang, Hanlin Wang, Wenjie Li
  arXiv:2405.16229, 2024.
  [arXiv]

• Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator

  Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, Huiping Zhuang
  Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
  [paper] [code]

Experiences

• 2023/08 - 2024/06: Research assistant at PolyU (Advisor: Prof. Maggie Wenjie Li)
• 2022/06 - 2023/03: Research assistant at ZeroNLP (Advisor: Prof. Ziqian Zeng)

Competitions&Honor

• [2023] Second Prize of 2023 South China University of Technology Challenge Cup
• [2022] First Prize in the “Hongping Evergreen Fund” Scholarship for Students' Scientific and Technological Innovation Competition
• [2022] Merit Student of SCUT
• [2022] Finalist of 2022 Mathematical Contest in Modeling
• [2022] Second Class School Scholarship
• [2021] Second Prize in the “Hongping Evergreen Fund” Scholarship for Students' Scientific and Technological Innovation Competition
• [2021] Merit Student of SCUT
• [2021] Second Prize of Asia-Pacific Cup Mathematical Contest in Modeling
• [2021] First Prize of The 2nd “The Greater Bay Area” Guangdong-Hong Kong-Macao Mathematical Modeling in Finance Contest

Professional Activities

Teaching Assistant

• COMP 6709: Advanced Natural Language Processing, Spring 2026, PolyU
• COMP 3531: Entrepreneurship, Spring 2025, PolyU
• COMP 4342: Mobile Computing, Fall 2024, PolyU

Reviewer

• ARR 2026 Jan
• ARR 2025 Feb (external)
• COLING 2025

Misc.

• I enjoy most outdoor sports (especially basketball, table tennis, and badminton). I also spend my leisure time on variety shows, literature books, and movies.

• I am eager to building Universal Robots with high IQ and EQ, benifit to the World. If you are also passionate with it, feel free to discuss!