I obtained my PhD degree in May 2026 from the Institute of Automation, Chinese Academy of Sciences, in the Brain Atlas and Brain-Inspired Intelligence Laboratory, under the supervision of Researcher Shan.Yu. I obtained my Bachelor of Engineering in Mechatronic Engineering from Beijing Institute of Technology, where I studied from 2017 to 2021.

Research Interest

My research lies at the intersection of computational neuroscience and artificial intelligence, with a focus on evaluating and enhancing high-level cognitive capabilities in large language models (LLMs) through brain-inspired cognitive mechanisms. Specifically, my work systematically investigates four dimensions: (1) cognitive flexibility assessment via neuropsychological paradigms; (2) cross-modal tool selection grounded in cognitive attribute representations; (3) episodic memory-augmented architectures for long-term context and persona consistency; and (4) multi-agent collaborative reasoning inspired by the Global Workspace Theory.

Publications

G. Hao, F. Alexandre and S. Yu, “Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test,” in IEEE Transactions on Cognitive and Developmental Systems, vol. 18, no. 1, pp. 228–238, Feb. 2026.

G. Hao, Y. Zhang, G. Ma, Y. Chen, F. Alexandre and S. Yu, “Large Language Models need Episodic Memory,” 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1–10, doi: 10.1109/IJCNN64981.2025.11229266.

Hao, Guangfu, Yang Chen, Sainan Qin, Frédéric Alexandre, and Shan Yu. “Self-Organized Context Dependent Processing in Neural Networks.” (Cognitive Computation, under review, Available at SSRN 5056172.).

Guangfu Hao, Haojie Wen, Liangxuna Guo, Yang Chen, Yanchao Bi, Shan Yu. Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language (Nature Communication, under review).

Yuhan Zhang, Guoqing Ma, Guangfu Hao, Liangxuan Guo, Yang Chen, Shan Yu. Efficient Reinforcement Learning through Adaptively Pretrained Visual Encoder (AAAI 2025).

Guoqing Ma, Yuhan Zhang, Yuming Dai, Guangfu Hao, Yang Chen, Shan Yu. Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning (IJCNN 2025).

Guoqing Ma, Yuhan Zhang, Yuming Dai, Guangfu Hao, Yang Chen, and Shan Yu. “Mitigating Non-Stationarity in Deep Reinforcement Learning with Clustering Orthogonal Weight Modification.” In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, pp. 2648–2650. 2025.

Liu MS, Gao JQ, Hu GY, Hao GF, Jiang TZ, Zhang C, Yu S. MonkeyTrail: A scalable video-based method for tracking macaque movement trajectory in daily living cages. Zool Res. 2022 May 18;43(3):343-351. doi: 10.24272/j.issn.2095-8137.2021.353. PMID: 35301830; PMCID: PMC9113979.

L. Guo, B. Zhu, Q. Tao, K. Liu, X. Zhao, X. Qin, J. Gao and G. Hao, “Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration,” arXiv preprint arXiv:2509.11067, 2025.

G. Hao, Y. Dai, X. Qin and S. Yu, “Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning,” arXiv preprint arXiv:2603.15371, 2026.