# Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence

arXiv: https://arxiv.org/abs/2409.06750 · HTML: https://mlsanity.com/paper/2409.06750/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 21 of 21)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2401.12863/) (2024)
- [Knowledge of cultural moral norms in large language models](https://mlsanity.com/paper/2306.01857/) (2023)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration](https://mlsanity.com/paper/2404.00405/) (2024)
- [Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents](https://mlsanity.com/paper/2305.02412/) (2023)
- [Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains](https://mlsanity.com/paper/2306.12028/) (2023)
- [CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM](https://mlsanity.com/paper/2401.03512/) (2024)
- [Do Multilingual Language Models Capture Differing Moral Norms?](https://mlsanity.com/paper/2203.09904/) (2022)
- [Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior](https://mlsanity.com/paper/2401.10910/) (2024)
- [ITCMA: A Generative Agent Based on a Computational Consciousness Structure](https://mlsanity.com/paper/2403.20097/) (2024)
- [The Tribal Theater Model: Social Regulation for Dynamic User Adaptation in Virtual Interactive Environments](https://mlsanity.com/paper/2403.13550/) (2024)
- [Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior Simulation](https://mlsanity.com/paper/2403.18230/) (2024)

## Built on by (most cited first, 5 of 5)

- [Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2507.21354/) (2025)
- [TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education](https://mlsanity.com/paper/2510.17913/) (2025)
- [Simulating Human Behavior with the Psychological-mechanism Agent: Integrating Feeling, Thought, and Action](https://mlsanity.com/paper/2507.19495/) (2025)
- [On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues](https://mlsanity.com/paper/2512.17060/) (2025)
- [SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments](https://mlsanity.com/paper/2607.00989/) (2026)

## Abstract (arXiv)

Generative agents have demonstrated impressive capabilities in specific tasks, but most of these frameworks focus on independent tasks and lack attention to social interactions. We introduce a generative agent architecture called ITCMA-S, which includes a basic framework for individual agents and a framework called LTRHA that supports social interactions among multi-agents. This architecture enables agents to identify and filter out behaviors that are detrimental to social interactions, guiding them to choose more favorable actions. We designed a sandbox environment to simulate the natural evolution of social relationships among multiple identity-less agents for experimental evaluation. The results showed that ITCMA-S performed well on multiple evaluation indicators, demonstrating its ability to actively explore the environment, recognize new agents, and acquire new information through continuous actions and dialogue. Observations show that as agents establish connections with each other, they spontaneously form cliques with internal hierarchies around a selected leader and organize collective activities.