Automated Design of Agentic Systems

Autor: Hu, Shengran, Lu, Cong, Clune, Jeff

Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine lea

Externí odkaz: http://arxiv.org/abs/2408.08435

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

Autor: Hu, Shengran, Clune, Jeff

Language is often considered a key aspect of human thinking, providing us with exceptional abilities to generalize, explore, plan, replan, and adapt to new situations. However, Reinforcement Learning (RL) agents are far from human-level performance i

Externí odkaz: http://arxiv.org/abs/2306.00323

Multi-objective Neural Architecture Search with Almost No Training

Autor: Hu, Shengran, Cheng, Ran, He, Cheng, Lu, Zhichao

In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries. Despite the steady stream of impressive empirical results, most existing NAS algorithms are computationally prohibitive to exec

Externí odkaz: http://arxiv.org/abs/2011.13591

The Absence of Intra‐Tumoral Tertiary Lymphoid Structures is Associated with a Worse Prognosis and mTOR Signaling Activation in Hepatocellular Carcinoma with Liver Transplantation: A Multicenter Retrospective Study.

Autor: Li, Jianhua^1,2 (AUTHOR), Zhang, Li³ (AUTHOR), Xing, Hao^1,2 (AUTHOR), Geng, Yan⁴ (AUTHOR), Lv, Shaocheng⁵ (AUTHOR), Luo, Xiao⁶ (AUTHOR), He, Weiqiao^1,2 (AUTHOR), Fu, Zhi⁷ (AUTHOR), Li, Guangming⁷ (AUTHOR), Hu, Bin^8,9 (AUTHOR), Jiang, Shengran^1,2 (AUTHOR), Yang, Zhe¹⁰ (AUTHOR), Zhu, Ningqi^1,2 (AUTHOR), Zhang, Quanbao^1,2 (AUTHOR), Zhao, Jing^1,2 (AUTHOR), Tao, Yifeng^1,2 (AUTHOR), Shen, Conghuan^1,2 (AUTHOR), Li, Ruidong^2,11 (AUTHOR), Tang, Feng¹² (AUTHOR), Zheng, Shusen¹⁰ (AUTHOR)

Publikováno v: Advanced Science. 6/5/2024, Vol. 11 Issue 21, p1-18. 18p.