Pangjing Wu吴庞敬

I am a PhD candidate at The Hong Kong Polytechnic University, supervised by Prof. Qing Li and Prof. Wenqi Fan.

I received my master's degree in Computer Science and bachelor's degree in Information and Computing Science from Hohai University, under the supervision of Prof. Xiaodong Li. My research connects large language models, data mining, reinforcement learning, and financial technology.

我目前在香港理工大学攻读博士学位，导师为李青教授和范文琦教授。

我于河海大学获得计算机科学硕士学位及信息与计算科学学士学位，硕士期间由李晓东教授指导。目前的研究聚焦于大语言模型、数据挖掘、强化学习与金融科技的交叉方向。

📧 pangjing.wu [at] outlook [dot] com 🎓 Google Scholar 💻 GitHub
Pangjing Wu speaking at an academic conference

Research Interests研究方向

My research interests include large language models, data mining, reinforcement learning, and financial technology. I am particularly interested in building intelligent systems that can reason, adapt, and make reliable decisions in complex and dynamic environments.

我的研究方向包括大语言模型、数据挖掘、强化学习与金融科技，重点关注如何构建能够在复杂动态环境中进行推理、适应并作出可靠决策的智能系统。

News最新动态

Our paper “Do You Truly Love Me?” Benchmarking LLM Capability on Hierarchical Pragmatic Tactic Conversations was accepted to AACL-IJCNLP 2026 Main.

我们的论文 “Do You Truly Love Me?” Benchmarking LLM Capability on Hierarchical Pragmatic Tactic Conversations 被 AACL-IJCNLP 2026 主会接收。

Our paper Dynamic Self-correcting Interaction Network was accepted to ACM Transactions on Information Systems (TOIS).

我们的论文 Dynamic Self-correcting Interaction Network 被 ACM Transactions on Information Systems (TOIS) 接收。

LLM-Powered KG Utility Evaluation Framework was published in IEEE Transactions on Knowledge and Data Engineering (TKDE).

LLM-Powered KG Utility Evaluation Framework 发表于 IEEE Transactions on Knowledge and Data Engineering (TKDE)。

Datamart-Agent was published in Findings of ACL 2026.

Datamart-Agent 发表于 ACL 2026 Findings。

Publications论文成果

† Co-first authors共同第一作者

‡ Supervisors导师

  1. AACL-IJCNLP 2026 Main

    “Do You Truly Love Me?” Benchmarking LLM Capability on Hierarchical Pragmatic Tactic Conversations

    Peter Q. Chen†, Pangjing Wu†, Zhuohang Jiang, Xiaodong Li‡, Peter H. F. Ng

    CORE BLLM

  2. ACM Transactions on Information Systems (TOIS)

    Dynamic Self-correcting Interaction Network

    Haoran Tang, Pangjing Wu, Shiqing Wu, Guandong Xu, Qing Li‡

    CCF AJCR Q1Recommender Systems

  3. Preprints

    From Solo Control to Enterprise Scale Through Agentic AI: A Survey of One-Person Agentic Company (OPAC)

    Yujuan Ding, Zihuai Zhao, Pangjing Wu, Chengliang Liu, Hanlou Zhang, Shanru Lin, Bill Pao, Dawei Yin, Na Zou, Jie Ye, et al.

    PreprintLLMAI Agents

  4. IEEE Transactions on Knowledge and Data Engineering (TKDE)

    LLM-Powered KG Utility Evaluation Framework

    Pangjing Wu, Xiaodong Li‡, Wenqi Fan‡, Qing Li‡

    CCF AJCR Q1LLMData-centric AI

  5. Findings of ACL 2026

    Datamart-Agent: LLM-Driven Game-Theoretic Agent for Data Marketplace Modeling

    Pangjing Wu, Peter Q. Chen, Xiaodong Li‡, Wenqi Fan‡, Qing Li‡

    CCF ACORE A*LLMData-centric AI

  6. AAMAS 2026

    Dynamic Action Space Reinforcement Learning for Optimal Trading Execution

    Pangjing Wu, Xiaodong Li‡

    CCF BCORE A*RLFinTech

  7. AAMAS 2026

    Timing Optimization in Dynamic Discrete Action Space Lifelong Reinforcement Learning

    Pangjing Wu, Xiaodong Li‡

    CCF BCORE A*RL

  8. KDD CUP 2025

    QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering

    Zhuohang Jiang†, Pangjing Wu†, Xu Yuan†, Wenqi Fan‡, Qing Li‡

    CCF ACORE A*LLM

  9. KDD 2025 Benchmark Track

    HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning

    Zhuohang Jiang†, Pangjing Wu†, Ziran Liang†, Peter Q. Chen†, Xu Yuan†, Ye Jia†, Jiancheng Tu†, Chen Li, Peter H. F. Ng, Qing Li‡

    CCF ACORE A*LLM

  10. ICDE 2025

    Towards Retrieval-Augmented Large Language Models: Data Management and System Design

    Wenqi Fan‡, Pangjing Wu, Yujuan Ding, Liangbo Ning, Shijie Wang, Qing Li‡

    CCF ACORE A*LLM
View earlier publications (10)查看早期论文（10 篇）

  1. IEEE Transactions on Big Data (TBD), 10(3), 288–300

    Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization

    Xiaodong Li‡, Pangjing Wu, Chenxin Zou, Qing Li‡

    CCF CJCR Q1RLFinTech

  2. arXiv:2304.00873

    Action Pick-up in Dynamic Action Space Reinforcement Learning

    Jiaqi Ye, Xiaodong Li‡, Pangjing Wu, Feng Wang

    PreprintRL

  3. IEEE Transactions on Affective Computing (TAFFC), 14(3), 1716–1730

    TSSRD: A Topic Sentiment Summarization Framework Based on Reaching Definition

    Xiaodong Li‡, Chenxin Zou, Pangjing Wu, Qing Li‡

    CCF BJCR Q1NLP

  4. ICSESS 2022

    Market Style Discrimination via Ensemble Learning

    Pangjing Wu, Xiaodong Li‡

    FinTech

  5. APWeb-WAIM 2022

    Many-to-Many Pair Trading

    Yingying Wang, Xiaodong Li‡, Pangjing Wu, Haoran Xie

    CCF CCORE CFinTech

  6. APWeb-WAIM 2022

    M2R: From Mathematical Models to Resource Description Framework

    Chenxin Zou, Xiaodong Li‡, Pangjing Wu, Haoran Xie

    CCF CCORE CData-centric AI

  7. Cognitive Computation (CC), 14(1), 149–166

    Stock Price Prediction Incorporating Market Style Clustering

    Xiaodong Li‡, Pangjing Wu

    JCR Q1FinTech

  8. Knowledge-Based Systems (KBS), 227, 107170

    Sentiment Lossless Summarization

    Xiaodong Li‡, Pangjing Wu, Chenxin Zou, Haoran Xie, Fu Lee Wang

    CCF CJCR Q1NLP

  9. IEEE Access, 7, 178342–178356

    Improving Order Execution Cost Estimation by Semisupervised Learning

    Xiaodong Li‡, Pangjing Wu, Rongrong Bo

    JCR Q2FinTech

  10. MLICOM 2019, 444–454

    Transaction Cost Analysis via Label-Spreading Learning

    Pangjing Wu, Xiaodong Li‡

    FinTech