LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?

TL;DR

This paper evaluates the capabilities and limitations of LLM-powered swarm systems, comparing them to classical algorithms, and finds that while they can mimic swarm behaviors, they face significant computational challenges.

Contribution

It provides a systematic comparison of classical and LLM-based swarm algorithms, highlighting the potential and current limitations of LLM-driven swarm intelligence.

Findings

LLM swarms can emulate classical swarm behaviors

LLM-based algorithms require significantly more computational resources

Current LLM swarms are limited for real-time applications

Abstract

Swarm intelligence describes how simple, decentralized agents can collectively produce complex behaviors. Recently, the concept of swarming has been extended to large language model (LLM)-powered systems, such as OpenAI's Swarm (OAS) framework, where agents coordinate through natural language prompts. This paper evaluates whether such systems capture the fundamental principles of classical swarm intelligence: decentralization, simplicity, emergence, and scalability. Using OAS, we implement and compare classical and LLM-based versions of two well-established swarm algorithms: Boids and Ant Colony Optimization. Results indicate that while LLM-powered swarms can emulate swarm-like dynamics, they are constrained by substantial computational overhead. For instance, our LLM-based Boids simulation required roughly 300x more computation time than its classical counterpart, highlighting current limitations in applying LLM-driven swarms to real-time systems.