# Challenges Faced by Large Language Models in Solving Multi-Agent Flocking

arXiv: https://arxiv.org/abs/2404.04752 · HTML: https://mlsanity.com/paper/2404.04752/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 6 Apr 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)
- [Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](https://mlsanity.com/paper/2309.15943/) (2023)
- [MathChat: Converse to Tackle Challenging Math Problems with LLM Agents](https://mlsanity.com/paper/2306.01337/) (2023)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Automatic Model Selection with Large Language Models for Reasoning](https://mlsanity.com/paper/2305.14333/) (2023)
- [Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following](https://mlsanity.com/paper/2302.14691/) (2023)
- [Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet](https://mlsanity.com/paper/2401.03630/) (2024)
- [Decentralized Multi-Agent Active Search and Tracking when Targets Outnumber Agents](https://mlsanity.com/paper/2401.03154/) (2024)
- [Stochastic Nonlinear Ensemble Modeling and Control for Robot Team Environmental Monitoring](https://mlsanity.com/paper/2212.11447/) (2022)

## Built on by (most cited first, 7 of 7)

- [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025)
- [A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives](https://mlsanity.com/paper/2503.13415/) (2025)
- [LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation](https://mlsanity.com/paper/2506.01538/) (2025)
- [Benchmarking LLMs' Swarm intelligence](https://mlsanity.com/paper/2505.04364/) (2025)
- [Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation](https://mlsanity.com/paper/2507.21969/) (2025)
- [GenSwarm: Scalable Multi-Robot Code-Policy Generation and Deployment via Language Models](https://mlsanity.com/paper/2503.23875/) (2025)
- [HEART: Coordination of Heterogeneous Expert Agents for Physically Grounded Robotic Task Planning](https://mlsanity.com/paper/2606.25404/) (2026)

## Abstract (arXiv)

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 natural disaster search and rescue, wild animal tracking, and perimeter surveillance and patrol. 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.