AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
2023/08/16 by Qingyun Wu, Wu, Qingyun, Gagan Bansal +26 · 3 voices · 428 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Natural Language Processing Techniques #Semantic Web and Ontologies #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2308.08155
openalex publication_date 2023/08/16 · arxiv published 2023/08/16 · openalex created_date 2023/08/18 · arxiv updated 2023/10/03 · openalex updated_date 2026/07/29
Abstract
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
Cited by
- From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
- MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
- NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code
- Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundations
- What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape
- State-dependent error correlations shape voting thresholds in committees of AI agents
- Recursive Governance: A Graph-Theoretic Framework for Risk Propagation and Drift Detection in Agentic AI Systems
- From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps
- SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
- Moral Hazard in Multi-Agent Language Models
- Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm
- Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation
- Towards an Agent Operating System - Lessons from Classical and Cloud OS
- Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams
- A Vocabulary for Multi-Agent Automated Research Systems
- When Coordination Is Avoidable: A Monotonicity Analysis of Organizational Tasks
- HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization
- What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization
- Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development
- A Plan Reuse Mechanism for LLM-Driven Agent
- Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks
- Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies
- CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications
- Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks
- Towards Interactive Intelligence for Digital Humans
- Differentiable Evolutionary Reinforcement Learning
- Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM
- GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
- Quantigence: A Multi-Agent AI Framework for Quantum Security Research
- Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution
- CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning
- Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs
- Adjudicator: Correcting Noisy Labels with a KG-Informed Council of LLM Agents
- FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
- A Multi-Agent LLM Framework for Design Space Exploration in Autonomous Driving Systems
- Towards a Science of Scaling Agent Systems
- Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels
- Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup
- ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment
- The Missing Layer of AGI: From Pattern Alchemy to Coordination Physics
- The Road of Adaptive AI for Precision in Cybersecurity
- RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design
- David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
- A Safety and Security Framework for Real-World Agentic Systems
- The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
- AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation
- Tipping the Dominos: Topology-Aware Multi-Hop Attacks on LLM-Based Multi-Agent Systems
- From static to adaptive: immune memory-based jailbreak detection for large language models
- PPTArena: A Benchmark for PowerPoint Editing
- Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents
- Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
- IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai
- Decentralized Multi-Agent System with Trust-Aware Communication
- LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
- Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs
- Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration
- CogEvo-Edu: Cognitive Evolution Educational Multi-Agent Collaborative System
- Toward a Safe Internet of Agents
- CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate
- NOMAD: A Multi-Agent LLM System for UML Class Diagram Generation from Natural Language Requirements
- Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation
- SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents
- DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs
- Learning Multi-Access Point Coordination in Agentic AI Wi-Fi with Large Language Models
- Latent Collaboration in Multi-Agent Systems
- Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
- A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis
- AutoMAS: A Generic Multi-Agent System for Algorithm Self-Adaptation in Wireless Networks
- MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference
- Z-Space: A Multi-Agent Tool Orchestration Framework for Enterprise-Grade LLM Automation
- Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems
- MURMUR: Using cross-user chatter to break collaborative language agents in groups
- IMACT-CXR: An Interactive Multi-Agent Conversational Tutoring System for Chest X-Ray Interpretation
- AISAC: An Integrated multi-agent System for Transparent, Retrieval-Grounded Scientific Assistance
- O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
- Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
- iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
- From Natural Language to Certified H-infinity Controllers: Integrating LLM Agents with LMI-Based Synthesis
- Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives
- Voice-Interactive Surgical Agent for Multimodal Patient Data Control
- AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models
- Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models
- PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization
- MTTR-A: Measuring Cognitive Recovery Latency in Multi-Agent Systems
- Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
- Catching Contamination Before Generation: Spectral Kill Switches for Agents
- TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
- Multi-Agent Collaborative Framework For Math Problem Generation
- Trustworthy LLM-Mediated Communication: Evaluating Information Fidelity in LLM as a Communicator (LAAC) Framework in Multiple Application Domains
- Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Models
- A Criminology of Machines
- Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
- CGF-DETR: Cross-Gated Fusion DETR for Enhanced Pneumonia Detection in Chest X-rays
- Efficient Test-Time Retrieval Augmented Generation
- MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
- GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents
- AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
- Validity Is What You Need
- MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models
- AgentBnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding
- ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Models
- OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research
- Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
- Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks
- UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
- Resolving Java Code Repository Issues with iSWE Agent
- Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models
- The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
- Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
- STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision
- The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
- Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft
- DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors
- Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
- When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
- Artificial Organisations
- CooperBench: Why Coding Agents Cannot be Your Teammates Yet
- MCP4IFC: IFC-Based Building Design Using Large Language Models
- StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems
- WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
- BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction
- MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
- Towards AI as Colleagues: Multi-Agent System Improves Structured Professional Ideation
- Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
- Compiler.next: A Search-Based Compiler to Power the AI-Native Future of Software Engineering
- From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
- ReCode: Unify Plan and Action for Universal Granularity Control
- Are Agents Just Automata? On the Formal Equivalence Between Agentic AI and the Chomsky Hierarchy
- TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generation
- Agentic Meta-Orchestrator for Multi-task Copilots
- Scalable Oversight via Partitioned Human Supervision
- Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration
- LightAgent: Mobile Agentic Foundation Models
- Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
- DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services
- Thought Communication in Multiagent Collaboration
- Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems
- AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation
- Fetch.ai: An Architecture for Modern Multi-Agent Systems
- Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning
- OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
- Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
- Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
- DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
- Experience-Driven Exploration for Efficient API-Free AI Agents
- The Spark Effect: On Engineering Creative Diversity in Multi-Agent AI Systems
- MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
- MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation
- Adaptive Minds: Empowering Agents with LoRA-as-Tools
- LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
- ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
- OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies
- NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension
- Agentic Discovery: Closing the Loop with Cooperative Agents
- Automated Network Protocol Testing with LLM Agents
- KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
- ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
- ParaCook: On Time-Efficient Planning for Multi-Agent Systems
- Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
- Automating Structural Engineering Workflows with Large Language Model Agents
- Scaling Agents for Computer Use
- The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
- PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
- DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
- KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
- HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
- D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
- GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
- Agentic Troubleshooting Guide Automation for Incident Management
- ALLOY: Generating Reusable Agent Workflows from User Demonstration
- SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
- SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study
- Deliberative Dynamics and Value Alignment in LLM Debates
- Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
- The Last Human-Written Paper: Agent-Native Research Artifacts
- Effective Strategies for Asynchronous Software Engineering Agents
- BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
- Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
- Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
- DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
- FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol
- CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
- Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
- Multimodal Safety Evaluation in Generative Agent Social Simulations
- Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines
- MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
- Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
- Measuring and Mitigating Identity Bias in Multi-Agent Debate via Anonymization
- ProSEA: Problem Solving via Exploration Agents
- L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
- Codified Context: Infrastructure for AI Agents in a Complex Codebase
- Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents
- Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents
- Training-Free Time Series Classification via In-Context Reasoning with LLM Agents
- ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
- Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis
- MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
- TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
- COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
- Zephyrus: An Agentic Framework for Weather Science
- NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
- AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning
- Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval
- Adversarial Agent Collaboration for C to Rust Translation
- TaskCraft: Automated Generation of Agentic Tasks
- JoyAgent-JDGenie: Technical Report on the GAIA
- Code2Video: A Code-centric Paradigm for Educational Video Generation
- Stochastic Self-Organization in Multi-Agent Systems
- CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage
- A Hierarchical Agentic Framework for Autonomous Drone-Based Visual Inspection
- Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
- CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
- The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
- DyFlow: Dynamic Workflow Framework for Agentic Reasoning
- AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment
- Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs
- LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
- PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
- Agentic Services Computing
- Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
- Dynamic Orchestration of Multi-Agent System for Real-World Multi-Image Agricultural VQA
- Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
- MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
- FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM Agents
- Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows
- CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
- The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution
- 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
- Generalized Multi-agent Social Simulation Framework
- Reimagining Agent-based Modeling with Large Language Model Agents via Shachi
- VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs
- Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning
- RepLLM: Toward Automatically Reproducing Network Research Results
- CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
- Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI
- Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
- RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents
- What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering
- FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification
- Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling
- Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
- Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale
- Agentic AutoSurvey: Let LLMs Survey LLMs
- Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge
- USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model
- OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama
- RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
- LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
- MICA: Multi-Agent Industrial Coordination Assistant
- PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning
- Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
- An LLM-based multi-agent framework for agile effort estimation
- An Empirical Study on Failures in Automated Issue Solving
- Evaluating Classical Software Process Models as Coordination Mechanisms for LLM-Based Software Generation
- 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
- EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer
- The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
- PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
- From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow
- MALLM: Multi-Agent Large Language Models Framework
- MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
- Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations
- The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
- Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
- Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis
- LightAgent: Production-level Open-source Agentic AI Framework
- Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
- Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
- Exploring Human-AI Collaboration Using Mental Models of Early Adopters of Multi-Agent Generative AI Tools
- AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
- Astra: A Multi-Agent System for GPU Kernel Performance Optimization
- SoK: Security and Privacy of AI Agents for Blockchain
- Simulating Dispute Mediation with LLM-Based Agents for Legal Research
- VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving
- Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents
- Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
- World Model Implanting for Test-time Adaptation of Embodied Agents
- Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems
- Plan Verification for LLM-Based Embodied Task Completion Agents
- Batch Query Processing and Optimization for Agentic Workflows
- Dynamic Speculative Agent Planning
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
- Communicative Agents for Slideshow Storytelling Video Generation based on LLMs
- CoComposer: LLM Multi-agent Collaborative Music Composition
- ORCA: ORchestrating Causal Agent
- Active Learning for Neurosymbolic Program Synthesis
- Operating advanced scientific instruments with AI agents that learn on the job
- Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence
- SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
- Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
- Network-Level Prompt and Trait Leakage in Local Research Agents
- STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
- Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions
- Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data
- Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
- Transduction is All You Need for Structured Data Workflows
- Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism
- COCO: Cognitive Operating System with Continuous Oversight for Multi-Agent Workflow Reliability
- Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks
- SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip
- A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial Applications
- Analyzing Information Sharing and Coordination in Multi-Agent Planning
- Synchronization Dynamics of Heterogeneous, Collaborative Multi-Agent AI Systems
- On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
- AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
- Allen: Rethinking MAS Design through Step-Level Policy Autonomy
- AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework
- Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
- Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration
- KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging
- Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
- LL3M: Large Language 3D Modelers
- Multi-agent systems for chemical engineering: A review and perspective
- SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detection
- Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
- MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media
- From MAS to MARS: Coordination Failures and Reasoning Trade-offs in Hierarchical Multi-Agent Robotic Systems within a Healthcare Scenario
- Training-Free Multimodal Large Language Model Orchestration
- RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
- An Auditable Agent Platform For Automated Molecular Optimisation
- CoAct-1: Computer-using Multi-Agent System with Coding Actions
- PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
- Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games
- BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability
- A Survey on Agent Workflow -- Status and Future
- WMAS: A Multi-Agent System Towards Intelligent and Customized Wireless Networks
- SWE-Exp: Experience-Driven Software Issue Resolution
- SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
- Opportunities and Challenges of LLMs in Education: An NLP Perspective
- Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
- FlowForge: Guiding the Creation of Multi-agent Workflows with Design Space Visualization as a Thinking Scaffold
- Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
- MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
- Efficient and Scalable Agentic AI with Heterogeneous Systems
- Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents
- Efficient Agents: Building Effective Agents While Reducing Cost
- Does More Inference-Time Compute Really Help Robustness?
- MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
- WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
- Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
- Think Like an Engineer: A Neuro-Symbolic Collaboration Agent for Generative Software Requirements Elicitation and Self-Review
- AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents
- Agyn: An Open-Source Platform for AI Agents with Scalable On-Demand Execution, Agent Definition as a Code, and Zero-Trust Access
- Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?
- uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs
- From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
- Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches
- AC4A: Access Control for Agents
- The Controllability Trap: A Governance Framework for Military AI Agents
- LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
- FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents
- Advancing Conversational Diagnostic AI with Multimodal Reasoning
- AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution
- Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
- MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning
- CAF-I: A Collaborative Multi-Agent Framework for Enhanced Irony Detection with Large Language Models
- From Semantic Web and MAS to Agentic AI: A Unified Narrative of the Web of Agents
- GoalfyMax: A Protocol-Driven Multi-Agent System for Intelligent Experience Entities
- Bridging Literature and the Universe Via A Multi-Agent Large Language Model System
- ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
- How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
- Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
- Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts
- KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
- Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
- EasyBCI Agent: Towards Universal Neural Data Preprocessing for Brain-Computer Interfaces
- ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
- Representing Prompting Patterns with PDL: Compliance Agent Case Study
- Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory
- AGACCI : Affiliated Grading Agents for Criteria-Centric Interface in Educational Coding Contexts
- TopoMAS: Large Language Model Driven Topological Materials Multiagent System
- FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios
- CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
- MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
- DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making
- Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation
- Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
- AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
- AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
- Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language Models
- Twill: Scheduling Compound AI Systems on Heterogeneous Mobile Edge Platforms
- Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning
- A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
- Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC
- LLM-guided Chemical Process Optimization with a Multi-Agent Approach
- Pay Attention to Small Weights
- Augmenting Multi-Agent Communication with State Delta Trajectory
- Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models
- TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation
- From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
- Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT
- Toward Autonomous UI Exploration: The UIExplorer Benchmark
- General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting
- SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2
- Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
- ChatAR: Conversation Support using Large Language Model and Augmented Reality
- LLM-based Satisfiability Checking of String Requirements by Consistent Data and Checker Generation
- StoryWriter: A Multi-Agent Framework for Long Story Generation
- StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework
- VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents
- OAgents: An Empirical Study of Building Effective Agents
- Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
- From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness
- SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
- How large language models can reshape collective intelligence
- LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs
- A Study on Individual Spatiotemporal Activity Generation Method Using MCP-Enhanced Chain-of-Thought Large Language Models
- Boosting LLM Reasoning via Spontaneous Self-Correction
- United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
- Can Theoretical Physics Research Benefit from Language Agents?
- Towards Next-Generation Intelligent Maintenance: Collaborative Fusion of Large and Small Models
- MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
- OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
- Toward Data Systems That Are Business Semantic Centric and AI Agents Assisted
- Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
- From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
- Agents of Change: Self-Evolving LLM Agents for Strategic Planning
- TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
Discussions
Related