Conference paper
Challenges Faced by Large Language Models in Solving Multi-agent Flocking
Distributed Autonomous Robotic Systems, v 34, pp 411-424
01 Jan 2026
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
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.
Metrics
2 Record Views
Details
- Title
- Challenges Faced by Large Language Models in Solving Multi-agent Flocking
- Creators
- Peihan Li - Drexel University, Electrical and Computer EngineeringVishnu Menon - Drexel Univ, Philadelphia, PA 19104 USABhavanaraj Gudiguntla - Drexel UniversityDaniel Ting - Drexel UniversityLifeng Zhou (Corresponding Author) - Drexel University, Electrical and Computer Engineering
- Publication Details
- Distributed Autonomous Robotic Systems, v 34, pp 411-424
- Conference
- 17th International Symposium on Distributed Autonomous Robotic Systems (DARS 2024), 17th (New York City, New York, United States, 27 Oct 2024–30 Oct 2024)
- Series
- Springer Proceedings in Advanced Robotics (SPAR); 34
- Publisher
- Springer Nature
- Number of pages
- 14
- Resource Type
- Conference paper
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:001748418000028
- Scopus ID
- 2-s2.0-105021937445
- Other Identifier
- 9783032045843; 3032045843; 991022189365604721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Automation & Control Systems
- Engineering, Electrical & Electronic
- Robotics