How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm

2026-04-13

AI Summary

This study investigates how memory length influences collective cooperation in large language model (LLM)-based multi-agent systems and reveals the critical role of model-specific characteristics, such as alignment strategies. By replacing rule-based agents in a social particle swarm model with LLM agents endowed with Big Five personality traits and variable memory lengths, simulations are conducted in a two-dimensional iterated prisoner’s dilemma environment. The work reports a novel finding: under identical memory configurations, Gemini-2.0-Flash and Gemma-3:4b exhibit starkly opposing cooperation dynamics—increased memory suppresses cooperation and triggers cluster collapse in the former, while promoting cooperation and dense clustering in the latter. Through sentiment analysis, the study identifies divergent cognitive interpretations of memory content between the two models as the fundamental mechanism driving this macro-level behavioral bifurcation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Modeling other Agents
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This study examines how model-specific characteristics of Large Language Model (LLM) agents, including internal alignment, shape the effect of memory on their collective and cooperative dynamics in a multi-agent system. To this end, we extend the Social Particle Swarm (SPS) model, in which agents move in a two-dimensional space and play the Prisoner's Dilemma with neighboring agents, by replacing its rule-based agents with LLM agents endowed with Big Five personality scores and varying memory lengths. Using Gemini-2.0-Flash, we find that memory length is a critical parameter governing collective behavior: even a minimal memory drastically suppressed cooperation, transitioning the system from stable cooperative clusters through cyclical formation and collapse of clusters to a state of scattered defection as memory length increased. Big Five personality traits correlated with agent behaviors in partial agreement with findings from experiments with human participants, supporting the validity of the model. Comparative experiments using Gemma~3:4b revealed the opposite trend: longer memory promoted cooperation, accompanied by the formation of dense cooperative clusters. Sentiment analysis of agents' reasoning texts showed that Gemini interprets memory increasingly negatively as its length grows, while Gemma interprets it less negatively, and that this difference persists in the early phase of experiments before the macro-level dynamics converge. These results suggest that model-specific characteristics of LLMs, potentially including alignment, play a fundamental role in determining emergent social behavior in Generative Agent-Based Modeling, and provide a micro-level cognitive account of the contradictions found in prior work on memory and cooperation.

Problem

• memory
• cooperation
• Large Language Models
• multi-agent systems
• collective behavior

Innovation

• LLM-based agents
• memory length
• collective behavior
• model-specific alignment
• Generative Agent-Based Modeling