awesome-multi-agent-papers
A compilation of the best multi-agent papers
https://github.com/kyegomez/awesome-multi-agent-papers
Last synced: 19 days ago
JSON representation
-
Social Simulation & Agent Societies
-
Other Domains
- Cultural Evolution of Cooperation among LLM Agents
- AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents
- OASIS: Open Agent Social Interaction Simulations with One Million Agents
- Generative Agents: Interactive Simulacra of Human Behavior
- Scaling Instructable Agents Across Many Simulated Worlds
- Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
- Scaling Synthetic Data Creation with 1,000,000,000 Personas
- From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models
- Mindstorms in Natural Language-Based Societies of Mind
- The AI Scientist: The world's first AI system for automating scientific research
- SDPO: Segment-Level Direct Preference Optimization for Social Agents
- SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents
- Agents' Room: Narrative Generation through Multi-step Collaboration
- GenSim: A General Social Simulation Platform with Large Language Model based Agents
- Large Language Models can Achieve Social Balance
-
-
Application-Specific Multi-Agent Systems
-
Multimodal
- MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception
- Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
- Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation
- Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
- PC-Agent: A Hierarchical Multi-Agent Framework for Complex Task Automation on PC
- Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
-
Other Domains
- Human-level play in Diplomacy by combining language models with strategic reasoning
- Beyond Human Translation: Multi-Agent Collaboration for Translating Ultra-Long Literary Texts
- CulturePark: Boosting Cross-cultural Understanding in Large Language Models
- Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Multi-Agent Collaboration
- FanCric: Multi-Agentic Framework for Crafting Fantasy 11 Cricket Teams
-
Software Engineering
- Experiential Co-Learning of Software-Developing Agents
- MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
- CodeR: Issue Resolving with Multi-Agent and Task Graphs
- CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
- Large Language Model-Based Agents for Software Engineering: A Survey
- AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation
- From LLMs to LLM-based Agents for Software Engineering: A Survey
- RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance
- Automated Unit Test Improvement using Large Language Models
- ChatDev: Communicative Agents for Software Development
- Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
-
Healthcare & Medical
-
Data & ML
- LAMBDA: A Large Model Based Data Agent
- Agentic Retrieval-Augmented Generation for Time Series Analysis
- Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining
- DataLab: A Unified Platform for LLM-Powered Business Intelligence
- AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
- AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
-
Security
-
-
Workflow, Architecture & Agent Design
-
Other Domains
- Enhancing Reasoning with Collaboration and Memory
- AgentInstruct: Toward Generative Teaching with Agentic Flows
- AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models
- Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
- Automated Design of Agentic Systems
- The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization
- SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
- Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
- Agents Thinking Fast and Slow: A Talker-Reasoner Architecture
- DynaSaur: Large Language Agents Beyond Predefined Actions
- LLMs as Method Actors: A Model for Prompt Engineering and Architecture
- When One LLM Drools, Multi-LLM Collaboration Rules
- AFlow: Automating Agentic Workflow Generation
- HERE
- Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
- AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models
- Multi-agent Architecture Search via Agentic Supernet
- Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
- Towards Collaborative Autonomous Research
- Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- open paper page
- HERE
-
-
Papers
- Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
- K-Level Reasoning with Large Language Models
- LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
- Automated Unit Test Improvement using Large Language Models
- AgentScope: A Flexible yet Robust Multi-Agent Platform
- Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- LLM Agent Operating System
- MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
- On scalable oversight with weak LLMs judging strong LLMs
- AgentInstruct: Toward Generative Teaching with Agentic Flows
- Scaling Instructable Agents Across Many Simulated Worlds
- Evolutionary Optimization of Model Merging Recipes
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
- CulturePark: Boosting Cross-cultural Understanding in Large Language Models
- Constitutional AI: Harmlessness from AI Feedback
- AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
- Mixture-of-Agents Enhances Large Language Model Capabilities
- CODER: ISSUE RESOLVING WITH MULTI-AGENT AND TASK GRAPHS
- EVOAGENT: Towards Automatic Multi-Agent: Generation via Evolutionary Algorithms
- Scaling Synthetic Data Creation with 1,000,000,000 Personas
- (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts
- Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
- Very Large-Scale Multi-Agent Simulation in AgentScope
- LAMBDA: A Large Model Based Data Agent
- From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models
- DIFFUSION AUGMENTED AGENTS: A FRAMEWORK FOR EFFICIENT EXPLORATION AND TRANSFER LEARNING
- Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
- The AI Scientist: The world’s first AI system for automating scientific research and open-ended discovery!
- CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
- Integrating Expertise of Software Engineering Agents
- The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation
- SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
- MEDCO: Medical Education Copilots Based on A Multi-Agent Framework
- Large Language Model-Based Agents for Software Engineering: A Survey
- AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
- Agentic Retrieval-Augmented Generation for Time Series Analysis
- Optimizing Collaboration of LLM based Agents for Finite Element
- SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
- HERE
- LLM-AGENT-UMF: LLM-BASED AGENT UNIFIED MODELING FRAMEWORK FOR SEAMLESS INTEGRATION OF MULTI ACTIVE/PASSIVE CORE-AGENTS
- Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
- HERE
- K-Level Reasoning with Large Language Models
- SCIAGENTS: AUTOMATING SCIENTIFIC DISCOVERY THROUGH MULTI-AGENT INTELLIGENT GRAPH REASONING ∗
-
Evaluation & Model Improvement
-
Other Domains
- Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Match Human Crowd Accuracy
- Evolutionary Optimization of Model Merging Recipes
- On scalable oversight with weak LLMs judging strong LLMs
- RouteLLM: An Open-Source Framework for Cost-Effective LLM Routing
- Constitutional AI: Harmlessness from AI Feedback
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debates
- MALT: Improving Reasoning with Multi-Agent LLM Training
- Why Do Multi-Agent LLM Systems Fail?
- Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
-
-
Multi-Agent Collaboration & System Design
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
- EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
- Mixture-of-Agents Enhances Large Language Model Capabilities
- Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
- Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning
- Optimizing Collaboration of LLM based Agents
- LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework
- Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
- LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
- AgentScope: A Flexible yet Robust Multi-Agent Platform
- AIOS: LLM Agent Operating System
- K-Level Reasoning with Large Language Models
- More Agents is All You Need
- Learning to Decode Collaboratively with Multiple Language Models
- Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
-
Multi-Agent Frameworks & Benchmarks
- Very Large-Scale Multi-Agent Simulation in AgentScope
- AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
- AgentClinic: A Multimodal Agent Benchmark for AI in Clinical Environments
- BoxingGym: Benchmarking Progress in Automated Experimental Design
- TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents
Categories