🎓 About Me

I am currently a Ph.D. candidate at The Hong Kong Polytechnic University (PolyU) under the supervision of Prof. HUANG Xiao with co-supervision by Prof. CHUNG Fu Lai Korris. Now, I am a visiting student at Nanyang Technological University (NTU) under the supervision of Prof. AN Bo. Before that, I obtained my BEng from Beihang University (BUAA) and MSc from National University of Singapore (NUS). My research interests include (Multi-Agent) Reinforcement Learning, Large Language Models (LLMs) Applications, and Fintech.

🎉 News

• [2026.02] Our survey on Graph-based Agent Memory is released. [Paper|Github]
• [2025.12] I was awarded the competitive grant ICRF (PolyU PhD Scholars International Collaborative Research Fellowship).
• [2025.06] I got the Best Poster Award in ARSC’25 (PolyU COMP - HKUST (GZ) INFH Research Student Conference).
• [2025.04] I passed the Ph.D. confirmation. Thanks to my supervisors and panel members Prof. YIU Man Lung Ken and Prof. LI Bo.

📔 Selected Publications (Full List)

[†]: Equal Contribution, [‡]: Corresponding Author

Preprint:

• [arXiv] Xinrun Wang†, Chang Yang†, He Zhao, Zhuoyi Lin, Shuyue Hu. The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents.
• [arXiv] Zhishang Xiang†, Chengyi Yang†, Zerui Chen, Zhimin Wei, Yunbo Tang, Zongpei Teng, Zexi Peng, Zongxia Li, Chengsong Huang, Yicheng He, Chang Yang, Xinrun Wang, Xiao Huang, Qinggang Zhang‡, Jinsong Su‡. A Systematic Survey of Self-Evolving Agents: From Model-Centric to Environment-Driven Co-Evolution.
• [arXiv] Yilin Xiao, Chuang Zhou, Yujing Zhang, Qinggang Zhang, Su Dong, Shengyuan Chen, Chang Yang, Xiao Huang. LAG: Logic-Augmented Generation from a Cartesian Perspective.
• [arXiv] Chang Yang†, Chuang Zhou†, Yilin Xiao†, Su Dong, Luyao Zhuang, Yujing Zhang, Zhu Wang, Zijin Hong, Zheng Yuan, Zhishang Xiang, Shengyuan Chen‡, Huachi Zhou‡, Qinggang Zhang‡, Ninghao Liu, Jinsong Su, Xinrun Wang, Yi Chang, Xiao Huang. Graph-based Agent Memory: Taxonomy, Techniques, and Applications.
• [arXiv] Junzhe Jiang†, Chang Yang†, Xinrun Wang‡, Zhiming Li, Xiao Huang, Bo Li. Resolving Latency and Inventory Risk in Market Making with Reinforcement Learning.
• [arXiv] Shuxin Li†, Chang Yang†, Youzhi Zhang, Pengdeng Li, Xinrun Wang‡, Xiao Huang, Hau Chan, Bo An. In-Context Exploiter for Extensive-Form Games.

Published:

• [EMNLP’26] Yujing Zhang, Huachi Zhou, Ruochen Liu, Qinggang Zhang, Luyao Zhuang, Hao Chen, Zijin Hong, Chang Yang, Xiao Huang. When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation.

• [KDD’26] Huachi Zhou, Jiahe Du‡, Yujing Zhang, Luyao Zhuang, Chang Yang, Zijin Hong, Jiaqi Bai, Qinggang Zhang, Kaixiong Zhou, Xiao Huang. ReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding. (AI4S Track)

• [TMLR’26] Chang Yang, Xinrun Wang‡, Junzhe Jiang, Qinggang Zhang, Xiao Huang. LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed.

• [ACL’26] Junzhe Jiang†, Chang Yang†, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Dongning Sun‡, Xinrun Wang‡. FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models. (Findings)

• [TMLR’26] Chang Yang†, Ruiyu Wang†, Junzhe Jiang, Qi Jiang, Qinggang Zhang, Yanchen Deng, Shuxin Li, Shuyue Hu, Bo Li, Florian T. Pokorny, Xiao Huang, Xinrun Wang‡. Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs. [Github|Leaderboard]

• [AAAI’26] Jiajun Cao, Qinggang Zhang‡, Yunbo Tang, Zhishang Xiang, Chang Yang, Jinsong Su‡. Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation.
  

• [EMNLP’25] Chang Yang, Xinrun Wang‡, Qinggang Zhang, Qi Jiang, Xiao Huang. Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning. (Findings)

• [ACL’25] Huachi Zhou†, Jiahe Du†, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang‡. Each Graph is a New Language: Graph Learning with LLMs. (Findings)

• [ICML’24] Pengdeng Li, Shuxin Li†, Chang Yang†, Xinrun Wang‡, Shuyue Hu, Xiao Huang, Hau Chan, Bo An. Configurable Mirror Descent: Towards a Unification of Decision Making.

• [IJCAI’24] Pengdeng Li, Shuxin Li†, Chang Yang†, Xinrun Wang‡, Xiao Huang, Hau Chan, Bo An. Self-adaptive PSRO: Towards an Automatic Population-based Game Solver.

• [IJCAI’24] Xinrun Wang†‡, Chang Yang†‡, Shuxin Li, Pengdeng Li, Xiao Huang, Hau Chan, Bo An. Reinforcement Nash Equilibrium Solver.
  

🏆 Honors and Awards

• [2025] PolyU Competitive ICRF (~$55,000HKD) and RSAP-Outgoing Grants
• [2025] PolyU ARSC’25 Best Poster Award
• [2021] BUAA Outstanding Graduate Award
• [2020] BUAA First-class Scholarship in Academic Contest
• [2018-2020] BUAA First/Second-class Scholarship ~ Three Times

💼 Academic Service

• Invited Reviewer: NeurIPS’26, ICLR’26, ACL’26, EMNLP’26, IJCAI(’25,’26), AAMAS’24
• Teaching Assistant: Database Systems (2023 Fall, 2025 Fall), Big Data Analytics (2024 Spring, 2024 Fall, 2025 Spring)