这一系列技术汇聚于开源平台LLM4AD[2]，其应用扩展至图像对抗攻击、流体力学建模[6]、飞行器设计乃至因果推断等上百个跨学科任务，展现出“大模型进化论”作为通用工具的无限潜能。
当算法开始自我进化，创新的边界便不再由人类预设的规则所限定。EoH及其引发的研究，正如一道穿透复杂性问题迷雾的轨迹。
此刻，你最想用这种“大模型进化论”，去自动设计一个什么领域的算法呢？
参考文献
[1] Liu, F., Tong, X., Yuan, M., Lin, X., Luo, F., Wang, Z., & Wang, Z. (2024). Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model. Nature Machine Intelligence.
[2] Romera, A. K., et al. (2024). LLM4AD: A Platform for Algorithm Design with Large Language Model. arXiv preprint arXiv:2412.17287.
[3] AgentAD Research Group. (2025). A Large Language Model-based Multi-Agent Framework to Autonomously Design Algorithms for Earth Observation Satellite Scheduling Problem. Engineering.
[4] Wang, Z., et al. (2026). LLM-assisted Adaptive Large Neighborhood Search for Agile Earth Observation Satellite Scheduling. Engineering Management.
[5] Liu, F., Liu, Y., Zhang, Q., Tong, X., & Yuan, M. (2026). EoH-S: Evolution of Heuristic Set Using LLMs for Automated Heuristic Design. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026).
[6] Zhang, Y., Zheng, K., Liu, F., Zhang, Q., & Wang, Z. (2025). AutoTurb: Using Large Language Models for Automatic Algebraic Model Discovery of Turbulence Closure. Physics of Fluids.
[7] Zhou, Y., et al. (2025). A Dual-Population Cooperative Evolution Framework for Agile Earth Observation Satellite Scheduling. European Journal of Operational Research.
[8] Chen, L., et al. (2024). LLaMEA: Large Language Model as Evolutionary Algorithm. Advances in Neural Information Processing Systems (NeurIPS).
[9] Xu, H., et al. (2025). ReEvo: Reflective Evolutionary Algorithm with Large Language Models. International Conference on Learning Representations (ICLR).
