AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
2023/08/21 by Chen, Weize, Su, Yusheng, Zuo, Jingwei +13 · 181 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2308.10848
Abstract
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \framework framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors among individual agents within a group during collaborative task accomplishment. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups. Our codes for \framework will soon be released at \urlhttps://github.com/OpenBMB/AgentVerse.
Cited by
- Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering
- Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams
- Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
- An Information Theoretic Perspective on Agentic System Design
- Multi-Agent LLM Committees for Autonomous Software Beta Testing
- Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
- Towards a Science of Scaling Agent Systems
- LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms
- MSME: A Multi-Stage Multi-Expert Framework for Zero-Shot Stance Detection
- Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks
- RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design
- Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation
- Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
- Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs
- CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows
- From Natural Language to Certified H-infinity Controllers: Integrating LLM Agents with LMI-Based Synthesis
- Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
- PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
- PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework
- Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
- The Collaboration Gap
- SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
- Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
- Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation
- How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm
- Ripple Effect Protocol: Coordinating Agent Populations
- Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
- How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
- ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
- DEBATE: A Large-Scale Benchmark for Role-Playing LLM Agents in Multi-Agent, Long-Form Debates
- MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
- Integrating LLM and Diffusion-Based Agents for Social Simulation
- Towards Scalable Oversight via Partitioned Human Supervision
- Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
- LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition
- Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication
- Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems
- A2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
- HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
- Failure-Driven Workflow Refinement
- Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
- Multimodal Safety Evaluation in Generative Agent Social Simulations
- Simulating Teams with LLM Agents: Interactive 2D Environments for Studying Human-AI Dynamics
- Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines
- Measuring and Mitigating Identity Bias in Multi-Agent Debate via Anonymization
- ProSEA: Problem Solving via Exploration Agents
- AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System
- ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
- Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails
- LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
- LLM Chemistry Estimation for Multi-LLM Recommendation
- AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
- JoyAgent-JDGenie: Technical Report on the GAIA
- Stochastic Self-Organization in Multi-Agent Systems
- CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage
- ACT: Agentic Classification Tree
- The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
- Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
- MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
- RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
- Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts
- Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
- RobustFlow: Towards Robust Agentic Workflow Generation
- Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning
- What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns
- Embodied AI: From LLMs to World Models
- FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification
- Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
- Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
- RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation
- Through the Lens of Human-Human Collaboration: A Configurable Research Platform for Exploring Human-Agent Collaboration
- Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making
- Aegis: Automated Error Generation and Attribution for Multi-Agent Systems
- AI Agents with Human-Like Collaborative Tools: Adaptive Strategies for Enhanced Problem-Solving
- From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
- Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
- Learning from Diverse Reasoning Paths with Routing and Collaboration
- PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
- DRF: LLM-AGENT Dynamic Reputation Filtering Framework
- Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
- LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
- Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance
- Building and Measuring Trust between Large Language Models
- FROGENT: An End-to-End Full-process Drug Design Multi-Agent System
- Exploring Large Language Model Agents for Piloting Social Experiments
- DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation
- Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges
- VirtLab: An AI-Powered System for Flexible, Customizable, and Large-scale Team Simulations
- DRAMA: A Dynamic and Robust Allocation-based Multi-Agent System for Changing Environments
- StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
- Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
- Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games
- A Survey on Agent Workflow -- Status and Future
- DynaSwarm: Dynamically Graph Structure Selection for LLM-based Multi-agent System
- Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
- MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
- From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems
- Agentic AI framework for End-to-End Medical Data Inference
- Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
- Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?
- A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
- GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems
- Aime: Towards Fully-Autonomous Multi-Agent Framework
- Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats
- ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
- FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
- AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
- HAWK: A Hierarchical Workflow Framework for Multi-Agent Collaboration
- AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
- Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges
- LLM-Based Social Simulations Require a Boundary
- Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
- OAgents: An Empirical Study of Building Effective Agents
- SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
- United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
- AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search
- From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
- TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
- Benchmarking LLMs' Swarm intelligence
- AI Agent Behavioral Science
- Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
- Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
- OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
- Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
- Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
- MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization
- Large Language Models Miss the Multi-Agent Mark
- HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
- AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
- Multi-Agent Collaboration via Evolving Orchestration
- Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
- Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
- MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
- MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework
- LLM-BSCVM: An LLM-Based Blockchain Smart Contract Vulnerability Management Framework
- Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
- Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development
- SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
- SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence
- X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
- MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
- Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization
- LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
- HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems
- Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
- HIERA: Hierarchical Multi-Agent Relevance Assessment for Content Discovery Systems
- Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
- Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures
- Emergence of Biased Consensus in Multi-Agent LLM Debates
- Benchmark Test-Time Scaling of General LLM Agents
- CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios
- Latent Cache Flow: Model-to-Model Communication Without Text
- APWA: A Distributed Architecture for Parallelizable Agentic Workflows
- PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement
- Contagion Networks: Evaluator Preference Propagation in Multi-Agent LLM Systems
- What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
- Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
- Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies
- LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
- Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
- Exploring Implicit Perspectives on Autism in Large Language Models Through Multi-Agent Simulations
- When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
- Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions
- Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
- FlowReasoner: Reinforcing Query-Level Meta-Agents
- SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation
- Planet as a Brain: Towards Internet of AgentSites based on AIOS Server
- CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation
- A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
- Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
- Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents
- Achilles Heel of Distributed Multi-Agent Systems
- EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design
- How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks
Related