A compilation of the best multi-agent papers <div align="left"> <a href="https://swarms.world"> <h1>Awesome Multi-Agent Papers</h1> </a> </div> <p align="left"> <a href="https://twitter.com/swarms_corp"> <picture> <source srcset="https://img.shields.io/badge/Twitter-Follow-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white" media="(prefers-color-scheme: dark)"> <img src="https://img.shields.io/badge/Twitter-Follow-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white" alt="Twitter"> </picture> </a> <a href="https://discord.gg/EamjgSaEQf"> <picture> <source srcset="https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white" media="(prefers-color-scheme: dark)"> <img src="https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"> </picture> </a> <a href="https://github.com/kyegomez/awesome-multi-agent-papers"> <picture> <source srcset="https://img.shields.io/badge/Awesome%20Multi-Agent%20Papers-Repo-000000?style=for-the-badge&logo=github&logoColor=white" media="(prefers-color-scheme: dark)"> <img src="https://img.shields.io/badge/Awesome%20Multi-Agent%20Papers-Repo-000000?style=for-the-badge&logo=github&logoColor=white" alt="Awesome Multi-Agent Papers"> </picture> </a> <a href="https://swarms.ai"> <picture> <source srcset="https://img.shields.io/badge/Swarms-Website-0A66C2?style=for-the-badge&logo=google-chrome&logoColor=white" media="(prefers-color-scheme: dark)"> <img src="https://img.shields.io/badge/Swarms-Website-0A66C2?style=for-the-badge&logo=google-chrome&logoColor=white" alt="Swarms Website"> </picture> </a> <a href="https://github.com/kyegomez/swarms"> <picture> <source srcset="https://img.shields.io/badge/Swarms-Framework-181717?style=for-the-badge&logo=github&logoColor=white" media="(prefers-color-scheme: dark)"> <img src="https://img.shields.io/badge/Swarms-Framework-181717?style=for-the-badge&logo=github&logoColor=white" alt="Swarms Framework"> </picture> </a> </p> <p align="left"> <em> This is an awesome list of the best multi-agent research papers, compiled by the <a href="https://github.com/kyegomez/swarms">Swarms</a> Team. Our mission at Swarms is to research multi-agent systems. <a href="https://discord.gg/EamjgSaEQf">Join our Discord Now!</a> </em> </p> --- ## Format - [Paper Name] [Description] [Link] ---- ## Multi-Agent Collaboration & System Design - **[Thought Communication in Multiagent Collaboration](https://arxiv.org/pdf/2510.20733)** - **[MAS-Zero: Designing Multi-Agent Systems with Zero Supervision](https://mas-design.github.io/)** - **[K-Level Reasoning with Large Language Models](https://arxiv.org/pdf/2402.01521)** - **[More Agents is All You Need](https://arxiv.org/pdf/2402.05120.pdf)** - **[LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration](https://arxiv.org/pdf/2402.11550)** - **[AgentScope: A Flexible yet Robust Multi-Agent Platform](https://arxiv.org/pdf/2402.14034.pdf)** - **[Learning to Decode Collaboratively with Multiple Language Models](https://arxiv.org/abs/2403.03870)** - **[AIOS: LLM Agent Operating System](https://arxiv.org/pdf/2403.16971.pdf)** - **[AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://arxiv.org/abs/2308.08155)** - **[Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://arxiv.org/abs/2406.02818)** - **[Mixture-of-Agents Enhances Large Language Model Capabilities](https://arxiv.org/abs/2406.04692)** - **[EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://arxiv.org/pdf/2406.14228)** - **[Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://arxiv.org/abs/2407.07061)** - **[Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning](https://arxiv.org/abs/2310.03094)** - **[Optimizing Collaboration of LLM based Agents](https://arxiv.org/pdf/2408.13406)** - **[LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework](https://arxiv.org/pdf/2409.11393)** - **[Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System](https://huggingface.co/papers/2410.08115)** - **[SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence](https://arxiv.org/pdf/2506.15672)** - **[AGENTSNET: Coordination and Collaborative Reasoning in Multi-Agent LLMs](https://www.arxiv.org/abs/2507.08616)** - **[LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra](https://arxiv.org/pdf/2507.15815)** - **[SOTOPIA-RL: REWARD DESIGN FOR SOCIAL INTELLIGENCE](https://arxiv.org/abs/2508.03905)** - **[Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://arxiv.org/abs/2509.05396)** - **[Virtual Agent Economies](https://huggingface.co/papers/2509.10147)** - **[Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI](https://arxiv.org/pdf/2509.20175)** - **[In-the-Flow Agentic System Optimization for Effective Planning and Tool Use](https://huggingface.co/papers/2510.05592)** - **[Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?](https://arxiv.org/html/2502.00674v1)** - **[TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture](https://arxiv.org/abs/2510.01279)** - **[Achilles Heel of Distributed Multi-Agent Systems](https://arxiv.org/abs/2504.07461)** - **[CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://arxiv.org/pdf/2303.17760.pdf)** - **[Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://api.semanticscholar.org/CorpusId:259088724)** - **[Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://arxiv.org/pdf/2402.18272.pdf)** - **[MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration](https://api.semanticscholar.org/CorpusId:265212971)** - **[LLM Harmony: Multi-Agent Communication for Problem Solving](https://api.semanticscholar.org/CorpusId:266725580)** - **[Multi-Agent Consensus Seeking via Large Language Models](https://arxiv.org/pdf/2310.20151.pdf)** - **[Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents](https://api.semanticscholar.org/CorpusId:267750197)** - **[Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models](https://api.semanticscholar.org/CorpusId:273654271)** - **[SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents](https://api.semanticscholar.org/CorpusId:273821018)** - **[Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10336211)** - **[A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis](https://arxiv.org/pdf/2504.12322)** - **[Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination](https://kjha02.github.io/publication/cross-env-coop)** - **[Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation](https://arxiv.org/abs/2511.02303)** - **[The Station: An Open-World Environment for AI-Driven Discovery](https://huggingface.co/papers/2511.06309)** - **[Towards a Science of Scaling Agent Systems](https://arxiv.org/abs/2512.08296)** - **[RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents](https://arxiv.org/abs/2601.18130)** - **[Intelligent AI Delegation](https://huggingface.co/papers/2602.11865)** - **[Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://huggingface.co/papers/2602.14299)** - **[Multi-agent cooperation through in-context co-player inference](https://huggingface.co/papers/2602.16301)** - **[SkillOrchestra: Learning to Route Agents via Skill Transfer](https://huggingface.co/papers/2602.19672)** - **[Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration](https://arxiv.org/abs/2603.06859)** [GitHub](https://github.com/facebookresearch/Hyperagents) - **[CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://huggingface.co/papers/2604.01658)** ## Multi-Agent Frameworks & Benchmarks - **[MALLM: Multi-Agent Large Language Models Framework](https://arxiv.org/abs/2509.11656)** - **[AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://huggingface.co/papers/2406.04151)** - **[Very Large-Scale Multi-Agent Simulation in AgentScope](https://arxiv.org/abs/2407.17789)** - **[AgentClinic: A Multimodal Agent Benchmark for AI in Clinical Environments](https://arxiv.org/pdf/2405.07960)** - **[MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents](https://arxiv.org/abs/2503.01935)** - **[TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://arxiv.org/abs/2412.14161)** - **[BoxingGym: Benchmarking Progress in Automated Experimental Design](https://arxiv.org/abs/2501.01540)** - **[Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence](https://arxiv.org/abs/2508.20019)** - **[CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards](https://huggingface.co/papers/2510.08529)** - **[The Collaboration Gap](https://huggingface.co/papers/2511.02687)** - **[API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://api.semanticscholar.org/CorpusId:258179056)** - **[AutoAgents: A Framework for Automatic Agent Generation](https://api.semanticscholar.org/CorpusId:263310605)** - **[MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems](https://api.semanticscholar.org/CorpusId:276781761)** - **[Multi-Agent Collaboration via Evolving Orchestration](https://openreview.net/pdf/9727f658d788c52f49f12ae4b230baf4cf0d4007.pdf)** - **[TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration](https://huggingface.co/papers/2601.04544)** - **[Context Learning for Multi-Agent Discussion](https://huggingface.co/papers/2602.02350)** - **[The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems](https://huggingface.co/papers/2602.15382)** - **[EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://arxiv.org/pdf/2603.02766)** ## Application-Specific Multi-Agent Systems ### Software Engineering - **[Automated Unit Test Improvement using Large Language Models](https://arxiv.org/pdf/2402.09171.pdf)** - **[Experiential Co-Learning of Software-Developing Agents](https://arxiv.org/abs/2312.17025)** - **[ChatDev: Communicative Agents for Software Development](https://arxiv.org/pdf/2307.07924.pdf)** - **[MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://arxiv.org/abs/2403.17927)** - **[CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://arxiv.org/pdf/2406.01304)** - **[From LLMs to LLM-based Agents for Software Engineering: A Survey](https://arxiv.org/abs/2408.02479)** - **[CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://www.arxiv.org/abs/2408.03910)** - **[Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents](https://arxiv.org/abs/2408.07060)** - **[Large Language Model-Based Agents for Software Engineering: A Survey](https://arxiv.org/pdf/2409.02977)** - **[AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation](https://arxiv.org/pdf/2409.10737)** - **[RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance](https://arxiv.org/pdf/2410.01242)** - **[CoAct-1: Computer-using Agents with Coding as Actions](https://arxiv.org/abs/2508.03923)** - **[Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization](https://arxiv.org/pdf/2404.02183.pdf)** - **[Human-In-the-Loop Software Development Agents](https://api.semanticscholar.org/CorpusId:274150430)** - **[LLM-Based Multi-Agent Systems for Software Engineering: Vision and the Road Ahead](https://api.semanticscholar.org/CorpusId:269005211)** - **[LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://api.semanticscholar.org/CorpusId:274965784)** - **[Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization](https://api.semanticscholar.org/CorpusId:268231438)** - **[Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents](https://api.semanticscholar.org/CorpusId:273482697)** - **[Scaling long-running autonomous coding](https://cursor.com/blog/scaling-agents)** A blog by Cursor - **[Towards self-driving codebases](https://cursor.com/blog/self-driving-codebases)** By Cursor - **[Harness Design for Long-Running Application Development](https://www.anthropic.com/engineering/harness-design-long-running-apps)** ### Healthcare & Medical - **[Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://arxiv.org/abs/2405.02957)** - **[MEDCO: Medical Education Copilots Based on A Multi-Agent Framework](https://arxiv.org/pdf/2408.12496)** - **[Multi Agent based Medical Assistant for Edge Devices](https://arxiv.org/pdf/2503.05397)** - **[Can AI Agents Design and Implement Drug Discovery Pipelines?](https://arxiv.org/abs/2504.19912)** - **[Sequential Diagnosis with Language Models](https://arxiv.org/pdf/2506.22405) ||Open-Source Implementation [Code Link](https://github.com/The-Swarm-Corporation/Open-MAI-Dx-Orchestrator)** - **[Towards an AI co-scientist](https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf)** --- [Implementation](https://github.com/The-Swarm-Corporation/AI-CoScientist) - **[The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies](https://www.nature.com/articles/s41586-025-09442-9)** - **[Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment](https://arxiv.org/abs/2603.21597)** - **[Evolving Diagnostic Agents in a Virtual Clinical Environment](https://huggingface.co/papers/2510.24654)** - **[MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://api.semanticscholar.org/CorpusId:269303028)** - **[Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics](https://api.semanticscholar.org/CorpusId:273098806)** - **[MADD: Multi-Agent Drug Discovery Orchestra](https://huggingface.co/papers/2511.08217)** - **[SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning](https://arxiv.org/pdf/2511.08151)** ### Data & ML - **[LAMBDA: A Large Model Based Data Agent](https://arxiv.org/abs/2407.17535)** - **[Agentic Retrieval-Augmented Generation for Time Series Analysis](https://arxiv.org/abs/2408.14484)** - **[Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining](https://huggingface.co/papers/2410.08102)** - **[AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://arxiv.org/pdf/2410.02958)** - **[AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions](https://arxiv.org/abs/2410.20424)** - **[DataLab: A Unified Platform for LLM-Powered Business Intelligence](https://arxiv.org/abs/2412.02205)** ### Security - **[BreachSeek: A Multi-Agent Automated Penetration Tester](https://arxiv.org/abs/2409.03789)** ### Multimodal - **[Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://arxiv.org/pdf/2403.13248)** - **[Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation](https://huggingface.co/papers/2406.01014)** - **[Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks](https://arxiv.org/abs/2408.03615)** - **[MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception](https://arxiv.org/abs/2312.07472)** - **[PC-Agent: A Hierarchical Multi-Agent Framework for Complex Task Automation on PC](https://arxiv.org/abs/2502.14282)** - **[Improving Large Vision and Language Models by Learning from a Panel of Peers](https://huggingface.co/papers/2509.01610)** - **[PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images](https://huggingface.co/papers/2509.25185)** - **[UFO: A UI-Focused Agent for Windows OS Interaction](https://api.semanticscholar.org/CorpusId:267636625)** - **[Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering](https://api.semanticscholar.org/CorpusId:274992537)** - **[Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10657391)** - **[Two Heads Are Better Than One: Collaborative LLM Embodied Agents for Human-Robot Interaction](https://api.semanticscholar.org/CorpusId:274281016)** - **[LongVideoAgent: Multi-Agent Reasoning with Long Videos](https://huggingface.co/papers/2512.20618)** ### Other Domains - **[Human-level play in Diplomacy by combining language models with strategic reasoning](https://www.science.org/doi/10.1126/science.ade9097)** - **[CulturePark: Boosting Cross-cultural Understanding in Large Language Models](https://arxiv.org/abs/2405.15145)** - **[Beyond Human Translation: Multi-Agent Collaboration for Translating Ultra-Long Literary Texts](https://arxiv.org/abs/2405.11804)** - **[FanCric: Multi-Agentic Framework for Crafting Fantasy 11 Cricket Teams](https://arxiv.org/pdf/2410.01307)** - **[Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Multi-Agent Collaboration](https://arxiv.org/pdf/2410.02507)** - **[SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction](https://huggingface.co/papers/2509.00581)** - **[CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games](https://aclanthology.org/2025.acl-long.389/)** - **[Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy](https://proceedings.neurips.cc/paper_files/paper/2024/hash/df2d62b96a4003203450cf89cd338bb7-Abstract-Conference.html)** - **[Large Language Model for Participatory Urban Planning](https://api.semanticscholar.org/CorpusId:268032947)** - **[Large language model empowered participatory urban planning](https://api.semanticscholar.org/CorpusId:267412207)** - **[Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice](https://api.semanticscholar.org/CorpusId:275119074)** - **[AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents](https://api.semanticscholar.org/CorpusId:271874640)** - **[MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting](https://api.semanticscholar.org/CorpusId:273532286)** - **[TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation](https://doi.org/10.5220/0013321900003890)** - **[Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances](https://api.semanticscholar.org/CorpusId:276576185)** - **[KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models](https://api.semanticscholar.org/CorpusId:271310037)** - **[A Multi-Agent Conversational Recommender System](https://api.semanticscholar.org/CorpusId:267406588)** - **[Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents](https://api.semanticscholar.org/CorpusId:270560396)** - **[Challenges Faced by Large Language Models in Solving Multi-Agent Flocking](https://api.semanticscholar.org/CorpusId:269004483)** - **[Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10610676)** - **[MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation](https://api.semanticscholar.org/CorpusId:274280893)** - **[ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise](https://api.semanticscholar.org/CorpusId:273654638)** - **[AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions](https://huggingface.co/papers/2602.06008)** ## Evaluation & Model Improvement - **[Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Match Human Crowd Accuracy](https://arxiv.org/abs/2402.19379)** - **[Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://arxiv.org/abs/2403.04132)** - **[Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems](https://arxiv.org/pdf/2403.02419.pdf)** - **[Evolutionary Optimization of Model Merging Recipes](https://arxiv.org/html/2403.13187v1)** - **[Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://arxiv.org/abs/2404.18796)** - **[Constitutional AI: Harmlessness from AI Feedback](https://arxiv.org/abs/2212.08073)** - **[On scalable oversight with weak LLMs judging strong LLMs](https://arxiv.org/abs/2407.04622)** - **[ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://arxiv.org/abs/2308.07201)** - **[RouteLLM: An Open-Source Framework for Cost-Effective LLM Routing](https://lmsys.org/blog/2024-07-01-routellm/)** - **[Agent-as-a-Judge: Evaluate Agents with Agents](https://arxiv.org/abs/2410.10934v1)** - **[Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debates](https://arxiv.org/pdf/2410.04663)** - **[MALT: Improving Reasoning with Multi-Agent LLM Training](https://arxiv.org/abs/2412.01928)** - **[Why Do Multi-Agent LLM Systems Fail?](https://arxiv.org/pdf/2503.13657)** - **[Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent](https://arxiv.org/pdf/2409.11527)** - **[The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind](https://arxiv.org/abs/2506.20664)** - **[Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL](https://arxiv.org/abs/2508.13167)** - **[Probe by Gaming: A Game-based Benchmark for Assessing Conceptual Knowledge in LLMs](https://arxiv.org/abs/2505.17512)** - **[The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://arxiv.org/abs/2509.02547)** - **[Stance Detection with Collaborative Role-Infused LLM-Based Agents](https://api.semanticscholar.org/CorpusId:264146255)** - **[Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)](https://api.semanticscholar.org/CorpusId:269042958)** - **[Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet](https://api.semanticscholar.org/CorpusId:266843945)** - **[Reliable Decision-Making for Multi-Agent LLM Systems](https://multiagents.org/2025_artifacts/reliable_decision_making_for_multi_agent_llm_systems.pdf)** - **[Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents](https://api.semanticscholar.org/CorpusId:276647196)** - **[AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://api.semanticscholar.org/CorpusId:268297202)** ## Social Simulation & Agent Societies - **[TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://arxiv.org/abs/2502.01506)** - **[Generative Agents: Interactive Simulacra of Human Behavior](https://arxiv.org/abs/2304.03442)** - **[SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://arxiv.org/pdf/2403.08715.pdf)** - **[Scaling Instructable Agents Across Many Simulated Worlds](https://huggingface.co/papers/2404.10179)** - **[Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://huggingface.co/papers/2406.20094)** - **[Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://arxiv.org/abs/2404.16698)** - **[From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models](https://arxiv.org/abs/2407.09502)** - **[Mindstorms in Natural Language-Based Societies of Mind](https://arxiv.org/abs/2305.17066)** - **[Agents' Room: Narrative Generation through Multi-step Collaboration](https://arxiv.org/pdf/2410.02603)** - **[GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://arxiv.org/pdf/2410.04360)** - **[Large Language Models can Achieve Social Balance](https://arxiv.org/pdf/2410.04054)** - **[Cultural Evolution of Cooperation among LLM Agents](https://arxiv.org/pdf/2412.10270)** - **[SDPO: Segment-Level Direct Preference Optimization for Social Agents](https://arxiv.org/abs/2501.01821)** - **[AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents](https://arxiv.org/abs/2502.08691v1)** - **[OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://arxiv.org/abs/2411.11581)** - **[LLM-Based Social Simulations Require a Boundary](https://arxiv.org/pdf/2506.19806)** - **[Social World Models](https://arxiv.org/abs/2509.00559)** - **[Simulating Human-like Daily Activities with Desire-driven Autonomy](https://arxiv.org/abs/2412.06435)** - **[Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations](https://aclanthology.org/2025.emnlp-main.1562/)** - **[Greater than the Sum of its Parts: Exploring Social Influence of Multi-Agents](https://doi.org/10.1145/3706599.3719973)** - **[Multi-Agents Are Social Groups: Investigating Social Influence of Multiple Agents in Human–Agent Interactions](https://dl.acm.org/doi/pdf/10.1145/3757633)** - **[Digital Red Queen: Adversarial Program Evolution in Core War with LLMs](https://pub.sakana.ai/drq/)** - **[Distributional AGI Safety: Governance Trade-offs in Multi-Agent Systems Under Adversarial Pressure](https://github.com/swarm-ai-safety/swarm)** ## Workflow, Architecture & Agent Design - **[AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models](https://huggingface.co/papers/2403.15157)** - **[AgentInstruct: Toward Generative Teaching with Agentic Flows](https://arxiv.org/abs/2407.03502)** - **[SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://arxiv.org/pdf/2409.05556)** - **[Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts](https://huggingface.co/papers/2409.13449)** - **[AFlow: Automating Agentic Workflow Generation](https://arxiv.org/pdf/2410.10762)** - **[Agents Thinking Fast and Slow: A Talker-Reasoner Architecture](https://arxiv.org/pdf/2410.08328)** - **[DynaSaur: Large Language Agents Beyond Predefined Actions](https://arxiv.org/pdf/2411.01747)** - **[LLMs as Method Actors: A Model for Prompt Engineering and Architecture](https://arxiv.org/abs/2411.05778v1)** - **[Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents](https://arxiv.org/abs/2412.13194)** - **[Automated Design of Agentic Systems](https://arxiv.org/abs/2408.08435)** - **[The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization](https://arxiv.org/pdf/2408.08688)** - **[Multi-agent Architecture Search via Agentic Supernet](https://arxiv.org/pdf/2502.04180)** - **[Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems](https://arxiv.org/abs/2502.11098)** - **[When One LLM Drools, Multi-LLM Collaboration Rules](https://arxiv.org/abs/2502.04506)** - **[Enhancing Reasoning with Collaboration and Memory](https://arxiv.org/pdf/2503.05944)** - **[Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning](https://huggingface.co/papers/2407.20798)** - **[Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://arxiv.org/abs/2410.10934v1)** - **[MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://huggingface.co/papers/2503.13964)** - **[Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution](https://huggingface.co/papers/2509.21072)** - **[Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation](https://huggingface.co/papers/2510.15624)** - **[Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1](https://huggingface.co/papers/2510.19600)** - **[Search Self-play: Pushing the Frontier of Agent Capability without Supervision](https://huggingface.co/papers/2510.18821)** - **[Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication](https://huggingface.co/papers/2510.19995)** - **[ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature](https://huggingface.co/papers/2510.20362)** - **[LLM Voting: Human Choices and AI Collective Decision Making](https://api.semanticscholar.org/CorpusId:267413124)** - **[Planning with Multi-Constraints via Collaborative Language Agents](https://api.semanticscholar.org/CorpusId:270063287)** - **[An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making](https://api.semanticscholar.org/CorpusId:273502378)** - **[Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface](https://api.semanticscholar.org/CorpusId:273023085)** - **[Prompt Engineering Through the Lens of Optimal Control](https://api.semanticscholar.org/CorpusId:264426100)** - **[A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition](https://api.semanticscholar.org/CorpusId:276618078)** - **[Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://api.semanticscholar.org/CorpusId:273346445)** - **[PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback](https://arxiv.org/pdf/2502.00988.pdf)** - **[Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework](https://arxiv.org/pdf/2403.19735.pdf)** ## Science - **[GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis](https://arxiv.org/abs/2406.15341)** - **[GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis](https://arxiv.org/abs/2507.21035)** - **[aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists](https://arxiv.org/abs/2508.15126)** - **[The AI Scientist: The world's first AI system for automating scientific research](https://arxiv.org/abs/2408.06292)** ## Alignment - **[The Alignment Waltz: Jointly Training Agents to Collaborate for Safety](https://arxiv.org/abs/2510.08240)** - **[MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization](https://api.semanticscholar.org/CorpusId:273233831)** ## Reinforcement Learning - **[MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning](https://api.semanticscholar.org/CorpusId:276580906)** - **[YOLO-MARL: You Only LLM Once for Multi-agent Reinforcement Learning](https://api.semanticscholar.org/CorpusId:273186556)** - **[LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions](https://api.semanticscholar.org/CorpusId:269921354)** - **[Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning](https://huggingface.co/papers/2601.09667)** - **[Scaling Multiagent Systems with Process Rewards](https://huggingface.co/papers/2601.23228)** ## Surveys - **[Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://api.semanticscholar.org/CorpusId:267412980)** - **[A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges](https://api.semanticscholar.org/CorpusId:273218743)** - **[Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://api.semanticscholar.org/CorpusId:275471465)** - **[A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application](https://api.semanticscholar.org/CorpusId:274981589)** - **[A Survey on Large Language Model based Autonomous Agents](https://arxiv.org/pdf/2308.11432.pdf)** - **[Large Language Models: A Survey](https://api.semanticscholar.org/CorpusId:267617032)** - **[LLM Multi-Agent Systems: Challenges and Open Problems](https://api.semanticscholar.org/CorpusId:267499950)** - **[Multi-Agent Coordination across Diverse Applications: A Survey](https://api.semanticscholar.org/CorpusId:276482652)** - **[LLM-based Multi-Agent Systems: Techniques and Business Perspectives](https://api.semanticscholar.org/CorpusId:274165614)** - **[Small LLMs Are Weak Tool Learners: A Multi-LLM Agent](https://www.aclanthology.org/2024.emnlp-main.929.pdf)** ## Others - **[PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs](https://huggingface.co/papers/2508.17188)** - **[MetaGPT: Meta Programming for Multi-Agent Collaborative Framework](https://doi.org/10.48550/arXiv.2308.00352)** - **[Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO](https://arxiv.org/abs/2511.13288)** ## Finance - **[TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://arxiv.org/abs/2502.01506)** - **[HedgeAgents: A Balanced-aware Multi-agent Financial Trading System](https://arxiv.org/abs/2502.13165)** ## Agents for Research - **[Towards Collaborative Autonomous Research](https://agentrxiv.github.io/)** ## Training - **[Latent Collaboration in Multi-Agent Systems](https://arxiv.org/abs/2511.20639)** ---- # Citations In the arxiv_bibtex.bib file, you can find the bibtex citations for all the papers in this repository. ## Cite This List If you find this resource useful in your research, please cite it as follows: **BibTeX:** ```bibtex @misc{gomez2024awesome, author = {Gomez, Kye}, title = {Awesome Multi-Agent Papers: A Compilation of the Best Multi-Agent Research}, year = {2024}, publisher = {GitHub}, journal = {GitHub Repository}, howpublished = {\url{https://github.com/kyegomez/awesome-multi-agent-papers}}, note = {Maintained by the Swarms Team. Contact: kye@swarms.world} } ``` **APA:** > Gomez, K. (2024). *Awesome Multi-Agent Papers: A Compilation of the Best Multi-Agent Research*. GitHub. https://github.com/kyegomez/awesome-multi-agent-papers **MLA:** > Gomez, Kye. "Awesome Multi-Agent Papers: A Compilation of the Best Multi-Agent Research." *GitHub*, 2024, https://github.com/kyegomez/awesome-multi-agent-papers. For questions or collaborations, contact: [kye@swarms.world](mailto:kye@swarms.world) # Contributing Have a multi-agent paper that isn’t on the list? We welcome your contributions! Please open a Pull Request (PR) to add new papers and help us maintain this comprehensive and up-to-date resource for the multi-agent research community. By contributing, you enable others—especially newcomers—to access the latest research in a single, centralized repository. Thank you for helping the community grow! # License This project is licensed under the [Apache License 2.0](LICENSE). Source: https://github.com/KyeGomezB/awesome-multi-agent-papers