.png){kind=icon}
Return
Challenges Faced by Large Language Models in Solving Multi-agent Flocking
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-04584-3_28.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Flocking is a behavior where multiple agents in a system attempt to stay close to each other while avoiding collision and maintaining a desired formation. This is observed in the natural world and has applications in robotics, including search and rescue, wild animal tracking, and perimeter surveillance. Recently, large language models (LLMs) have displayed an impressive ability to solve various collaboration tasks as individual decision-makers. Solving multi-agent flocking with LLMs would demonstrate their usefulness in situations requiring spatial and decentralized decision-making. Yet, when LLM-powered agents are tasked with implementing multi-agent flocking, they fall short of the desired behavior. After extensive testing, we find that agents with LLMs as individual decision-makers typically opt to converge on the average of their initial positions or diverge from each other. After breaking the problem down, we discover that LLMs cannot understand maintaining a shape or keeping a distance in a meaningful way. Solving multi-agent flocking with LLMs would enhance their ability to understand collaborative spatial reasoning and lay a foundation for addressing more complex multi-agent tasks. This paper discusses the challenges LLMs face in multi-agent flocking and suggests areas for future improvement and research.
Keywords:
Large language models (LLMs)
multi-agent systems
flocking
Journal
D
IF:
0
Papers:
22
Citations:
0
Organization
Cited Papers
ShareSaveShareSaveFlocking for Multiple Subgroups of Multi-Agents With Different Social Distancing.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSave
View more