Kejiang "Brian" Qian
I am a PhD student in the EPSRC CDT in Machine Learning Systems at the University of Edinburgh, supervised by Dr. Fengxiang He and Prof. Amos Storkey since September 2024. My research focuses on reinforcement learning agents, large language model agents, and interpreting their behaviours through the lens of rationality.
For the full list of publications, see my Google Scholar. Comments are always welcome.
Kejiang Qian, Fengxiang He. In LLM Reasoning, there is Irrationality on top of Value Misalignment. arXiv preprint arXiv:2606.20624, 2026.
Kejiang Qian, Amos Storkey, Fengxiang He. Rationality Measurement and Theory for Reinforcement Learning Agents. International Conference on Machine Learning (ICML), 2026.
Finn van der Knaap, Kejiang Qian, Zheng Xu, Fengxiang He. PRISM: Parallel Reward Integration with Symmetry for MORL. arXiv preprint arXiv:2602.18277, 2026.
Wenbin Wu, Kejiang Qian, Alexis Lui, Christopher Jack, Yue Wu, Peter McBurney, Fengxiang He, Bryan Zhang. DeXposure: A Dataset and Benchmarks for Inter-protocol Credit Exposure in Decentralized Financial Networks. arXiv preprint arXiv:2511.22314, 2025.
Archived website · Last updated: