Awesome Generative Multi-Agent Systems

A curated list of awesome resources, libraries, frameworks, and tools for generative multi-agent systems research and development.

Economics & Finance

• EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities (Paper)
• SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series (Paper)
• The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games? (Paper)
• “Guinea Pig Trials” Utilizing GPT: A Novel Smart Agent-Based Modeling Approach for Studying Firm Competition and Collusion (Paper)
• ABIDES-Economist: Agent-Based Simulation of Economic Systems with Learning Agents (Paper)
• Simulating Financial Market via Large Language Model based Agents (Paper)
• A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist (Paper)
• FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design (Paper)
• FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models (Paper)
• Agentic Retrieval-Augmented Generation for Time Series Analysis (Paper)
• Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy (Paper)
• FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
• InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma

Social

• Generative Agents: Interactive Simulacra of Human Behavior (Paper)
• Social Simulacra: Creating Populated Prototypes for Social Computing Systems (Paper)
• S3: Social-network Simulation System with Large Language Model-Empowered Agents (Paper)
• Predicting Twitter Engagement With Deep Language Models (Paper)
• Language models trained on media diets can predict public opinion (Paper)
• Simulating social media using large language models to evaluate alternative news feed algorithms. (Paper)
• Improving interpersonal communication by simulating audiences with language models (Paper)
• Simulating Family Conversations using LLMs: Demonstration of Parenting Styles (Paper)
• Y Social: an LLM-powered Social Media Digital Twin (Paper)
• OASIS: Open Agent Social Interaction Simulations with One Million Agents

Science

• SCIENCEWORLD: Is your Agent Smarter than a 5th Grader? (Paper)
• DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents (Paper)
• ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs (Paper)
• Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design (Paper)
• ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning (Paper)
• AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence (Paper)
• MARG: Multi-Agent Review Generation for Scientific Papers (Paper)
• Empowering Biomedical Discovery with AI Agents (Paper)
• LLM-Collaboration on Automatic Science Journalism for the General Audience (Paper)
• LLM experiments with simulation: Large Language Model Multi-Agent System for Process Simulation Parametrization in Digital Twins (Paper)
• SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
• Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation (Paper)

Software Development

• MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution (Paper)

Health

• Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents (Paper)
• MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (Paper)
• Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles (Paper)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator (Paper)
• AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments (Paper)
• Exploring LLM Multi-Agents for ICD Coding (Paper)
• Epidemic Modeling with Generative Agents (Paper)
• MEDCO: Medical Education Copilots Based on A Multi-Agent Framework (Paper)
• MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance (Paper)

Education

• CGMI: Configurable General Multi-Agent Interaction Framework (Paper)
• GPTeach: Interactive TA Training with GPT-based Students (Paper)
• Simulating Classroom Education with LLM-Empowered Agents (Paper)
• EduAgent: Generative Student Agents in Learning (Paper)
• MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education (Paper)

Translation

• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts (Paper)

Industry

• Towards autonomous system: flexible modular production system enhanced with large language model agents (Paper)
• Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0 (Paper)
• An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems (Paper)
• Large Language Model-Enabled Multi-Agent Manufacturing Systems (Paper)
• A Large Language Model-based multi-agent manufacturing system for intelligent shopfloor (Paper)
• MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities (Paper)

Recruitment

• MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents (Paper)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors (Paper)

User Research

• User Behavior Simulation with Large Language Model based Agents (Paper)
• AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems (Paper)
• Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation (Paper)
• User Behavior Simulation with Large Language Model based Agent (Paper)
• BASES: large-scale web search user simulation with large language model based agents (Paper)
• Elicitron: An LLM Agent-Based Simulation Framework for Design Requirements Elicitation (Paper)

Gaming

• StoryVerse: Towards Co-authoring Dynamic Plot with LLM-based Character Simulation via Narrative Planning (Paper)
• MindAgent: Emergent Gaming Interaction (Paper)
• Digital Life Project: Autonomous 3D Characters with Social Intelligence (Paper)
• Conversational Interactions with NPCs in LLM-Driven Gaming: Guidelines from a Content Analysis of Player Feedback (Paper)
• Fictional Worlds, Real Connections: Developing Community Storytelling Social Chatbots through LLMs (Paper)
• Towards a Holodeck-style Simulation Game (Paper)

Game Theory

• Game-theoretic LLM: Agent Workflow for Negotiation Games (Paper, Code)

Security

• Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments (Paper)

Law

• SimuCourt: Building Judicial Decision-Making Agents with Real-world Judgement Documents (Paper)
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models (Paper)

Governance

• Simulating The U.S. Senate: An LLM-Driven Agent Approach to Modeling Legislative Behavior and Bipartisanship (Paper)
• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents (Paper)
• Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulation (Paper)

Urban Planning

• Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment (Paper)
• Large Language Model for Participatory Urban Planning (Paper)
• Simulating Public Administration Crisis: A Novel Generative Agent-Based Simulation System to Lower Technology Barriers in Social Science Research (Paper)
• Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation (Paper)
• PedSUMO: Simulacra of Automated Vehicle-Pedestrian Interaction Using SUMO To Study Large-Scale Efects (Paper)
• Generative agents in the streets: Exploring the use of Large Language Models (LLMs) in collecting urban perceptions (Paper)
• GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning (Paper)
• GRUtopia: Dream General Robots in a City at Scale (Paper)
• SurrealDriver: Designing Generative Driver Agent Simulation Framework in Urban Contexts based on Large Language Model (Paper)

Geopolitics

• Modelling Political Coalition Negotiations Using LLM-based Agents (Paper)
• BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis (Paper)
• War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars (Paper)
• Human vs. Machine: Behavioral Differences between Expert Humans and Language Models in Wargame Simulations (Paper)

Aliens

• What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents (Paper)

General

• Mixture-of-Agents Enhances Large Language Model Capabilities (Paper)
• More Agents Is All You Need (Paper)
• Mindstorms in Natural Language-Based Societies of Mind (Paper)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence (Paper)