README.md

Awesome Multi-Agent Papers

A compilation of the best multi-agent papers

🐦 Twitter   •   📢 Discord   •   Swarms Platform   •   📙 Framework

A compilation of the best multi-agent papers by the Swarms Team. Our mission is to democratize multi-agent systems to automate the world economy with agents and usher in a post-scarcity Human civilization. Join our community now!

Format

• [Paper Name] ([PDF PAPER LINK ]) bibtex short name

---

Papers

• K-Level Reasoning with Large Language Models, zhang2024240201521

• More agents is all you need,li2024240205120

• LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration , zhao2024240211550

• Automated Unit Test Improvement using Large Language Models , alshahwan2024240209171

• Human-level play in the game of Diplomacy by combining language models with strategic reasoning

• AgentScope: A Flexible yet Robust Multi-Agent Platform , gao2024240214034

• Experiential Co-Learning of Software-Developing Agents,qian2023231217025

• ChatDev: Communicative Agents for Software Development, qian2023230707924

• Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Match Human Crowd Accuracy, schoenegger2024240219379

• Generative Agents: Interactive Simulacra of Human Behavior park2023230403442

• Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems, chen2024240302419

• Learning to Decode Collaboratively with Multiple Language Models, shen2024240303870

• Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference, chiang2024240304132

• SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents, wang2024240308715

• Mora: Enabling Generalist Video Generation via A Multi-Agent Framework, yuan2024240313248

• AIOS: LLM Agent Operating System, mei2024240316971

• MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution, tao2024240317927

• AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models, zhang2024240315157

• Scaling Instructable Agents Across Many Simulated Worlds, team2024240410179

• Evolutionary Optimization of Model Merging Recipes, akiba2024240313187

• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models, verga2024240418796

• Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents, li2024240502957

• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation, wu2023230808155

• Chain of Agents: Large Language Models Collaborating on Long-Context Tasks, zhang2024240602818

• CulturePark: Boosting Cross-cultural Understanding in Large Language Models, li2024240515145

• Constitutional AI: Harmlessness from AI Feedback, bai2022221208073

• Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration, wang2024240601014

• Mixture-of-Agents Enhances Large Language Model Capabilities, wang2024240604692

• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments, xi2024240604151

• CodeR: Issue Resolving with Multi-Agent and Task Graphs, chen2024240601304

• EvoAgent: Towards Automatic Multi-Agent: Generation via Evolutionary Algorithms, yuan2024240614228

• Scaling Synthetic Data Creation with 1,000,000,000 Personas, ge2024240620094

• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts, wu2024240511804

• RouteLLM: An Open-Source Framework for Cost-Effective LLM Routing, ong2024240618665

• On scalable oversight with weak LLMs judging strong LLMs, kenton2024240704622

• AgentInstruct: Toward Generative Teaching with Agentic Flows, mitra2024240703502

• On scalable oversight with weak LLMs judging strong LLMs

• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents, piatti2024240416698

• Very Large-Scale Multi-Agent Simulation in AgentScope, pan2024240717789

• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents , piatti2024cooperatecollapseemergencesustainable

• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence, chen2024240707061

• LAMBDA: A Large Model Based Data Agent, sun2024240717535

• Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning, palo2024240720798

• From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models, nisioti2024240709502

• Mindstorms in Natural Language-Based Societies of Mind, zhuge2023230517066

• Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning, yue2023231003094

• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate, chan2023230807201

• From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future, jin2024240802479

• Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks, li2024240803615

• The AI Scientist: The world’s first AI system for automating scientific research and open-ended discovery!, lu2024240806292

• CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases, liu2024240803910

• Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents, zhang2024240807060

• Automated Design of Agentic Systems, hu2024240808435

• The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation, arif2024240808688

• MEDCO: Medical Education Copilots Based on A Multi-Agent Framework, wei2024240812496

• Agentic Retrieval-Augmented Generation for Time Series Analysis, ravuru2024240814484

• Optimizing Collaboration of LLM based Agents for Finite Element, tian2024240813406

• BreachSeek: A Multi-Agent Automated Penetration Tester, alshehri2024240903789

• SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning, ghafarollahi2024240905556

• Large Language Model-Based Agents for Software Engineering: A Survey, liu2024240902977

• SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

• AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing, nunez2024240910737

• Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent, haji2024240911527,

• LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Integration of Multi Active/Passive Core-Agents, assouna2024240911393

• Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts, wang2024240913449

• Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration, yuan2024241002507

• FanCric: Multi-Agentic Framework for Crafting Fantasy 11 Cricket Teams, bhatnagar2024241001307

• RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance, jin2024241001242

• Agents' Room: Narrative Generation through Multi-step Collaboration, huot2024241002603

• GenSim: A General Social Simulation Platform with Large Language Model based Agents, tang2024241004360

• Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debates, bandi2024241004663

• Large Language Models can Achieve Social Balance, cisneros-velarde2024241004054

• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML, trirat2024241002958

• Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining, bai2024241008102

• Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System, chen2024241008115

• Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

• Agent-as-a-Judge: Evaluate Agents with Agents, zhuge2024241010934

• AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions, li2024241020424

• AFlow: Automating Agentic Workflow Generation, zhang2024241010762

• Agents Thinking Fast and Slow: A Talker-Reasoner Architecture, christakopoulou2024241008328

• AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments, schmidgall2024agentclinicmultimodalagentbenchmark

• DynaSaur: Large Language Agents Beyond Predefined Actions, nguyen2024241101747

• LLMs as Method Actors: A Model for Prompt Engineering and Architecture, doyle2024llmsmethodactorsmodel

• DataLab: A Unifed Platform for LLM-Powered Business Intelligence, schmidgall2024agentclinicmultimodalagentbenchmark

• Cultural Evolution of Cooperation among LLM Agents, vallinder2024culturalevolutioncooperationllm

---

Citations

In the arxiv_bibtex.bib file, you can find the bibtex citations for all the papers in this repository.

Community

Join the multi-agent community now on discord HERE