Exploring large language model based intelligent agents: Definitions, methods, and prospects

Y Cheng, C Zhang, Z Zhang, X Meng, S Hong… - arxiv preprint arxiv …, 2024 - arxiv.org
Intelligent agents stand out as a potential path toward artificial general intelligence (AGI).
Thus, researchers have dedicated significant effort to diverse implementations for them …

A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback

AR Laleh, MN Ahmadabadi - arxiv preprint arxiv:2411.13410, 2024 - arxiv.org
Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating
remarkable potential in tackling real-world challenges. Despite its promising prospects, this …

LLM-empowered state representation for reinforcement learning

B Wang, Y Qu, Y Jiang, J Shao, C Liu, W Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Conventional state representations in reinforcement learning often omit critical task-related
details, presenting a significant challenge for value networks in establishing accurate …

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

F Zhang, J Li, YC Li, Z Zhang, Y Yu, D Ye - arxiv preprint arxiv …, 2024 - arxiv.org
Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the
advent of versatile large language models (LLMs), recent works impart common-sense …

[PDF][PDF] Position: Towards LLM-in-the-Loop Machine Learning for Future Applications

M Hong, W Ng, Y Wang, D Jiang, Y Song, CJ Zhang… - researchgate.net
Building on the success of human-in-the-loop, where human wisdom is integrated into the
development of machine learning algorithms, we take the initiative to envision an innovative …