mlsanityData to 7 Oct 2026

MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs

arXiv 2408.09955 ↗First posted 19 Aug 2024cs.MAcited by 45

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptional performance, successfully developing a Gobang game within 800 seconds and scaling up to 590 agents in a national policy simulation to generate multi-domain policies. It significantly outperforms existing systems, such as MetaGPT, in both task completion efficiency and scalability. By eliminating the need for predefined SOPs, MegaAgent demonstrates exceptional scalability and autonomy, setting a foundation for advancing true autonomy in MAS. Our code is available at https://github.com/Xtra-Computing/MegaAgent .

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 54 of its 90 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

54 of 90 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Very Large-Scale Multi-Agent Simulation in AgentScope25 Jul
  2. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration23 May
  3. 2024TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation8 Feb
  4. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents2 Feb
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct
  6. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 47

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  8. 2021Program Synthesis with Large Language Modelscited by 3,509
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  10. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
35 more
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  3. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  4. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  5. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  6. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  7. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  8. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  9. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  10. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  11. 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decodingcited by 295
  12. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  13. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  14. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 143
  15. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agentscited by 120
  16. 2020Serving DNNs like Clockwork: Performance Predictability from the Bottom Upcited by 119
  17. 2024AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulatorcited by 99
  18. 2024Parrot: Efficient Serving of LLM-based Applications with Semantic Variablecited by 96
  19. 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisiscited by 88
  20. 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipelinecited by 86
  21. 2017TensorFlow-Serving: Flexible, High-Performance ML Servingcited by 85
  22. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 84
  23. 2023S3: Increasing GPU Utilization during Generative Inference for Higher Throughputcited by 81
  24. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  25. 2021Machine Translation Decoding beyond Beam Searchcited by 55
  26. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  27. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Taskscited by 52
  28. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Frameworkcited by 47
  29. 2024Transfer Q Star: Principled Decoding for LLM Alignmentcited by 46
  30. 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45
  31. 2024Simulating Financial Market via Large Language Model based Agentscited by 25
  32. 2023BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detectioncited by 19
  33. 2023Can Transformers Learn to Solve Problems Recursively?cited by 17
  34. 2024What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agentscited by 12
  35. 2023Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFTcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 30.

45 papers.

Sort:

By area:

  1. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 58
  2. 2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inferencecited by 57
  3. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 48
  4. 2025GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveragingcited by 25
  5. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  6. 20251-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoningcited by 16
  7. 2026Effective Strategies for Asynchronous Software Engineering Agentscited by 12
  8. 2025Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM Systemcited by 10
  9. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  10. 2025CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMscited by 9
  11. 2025AutoTool: Efficient Tool Selection for Large Language Model Agentscited by 9
  12. 2025Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challengecited by 8
33 more
  1. 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviorscited by 7
  2. 2026RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reusecited by 6
  3. 2026LLM Review: Enhancing Creative Writing via Blind Peer Review Feedbackcited by 4
  4. 2025AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Modelscited by 3
  5. 2026Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)cited by 3
  6. 2025PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Frameworkcited by 2
  7. 2026SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generationcited by 2
  8. 2026CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experimentscited by 2
  9. 2025AI Compute Architecture and Evolution Trendscited by 1
  10. 2025Reflection-Driven Control for Trustworthy Code Agentscited by 1
  11. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answeringcited by 1
  12. 2026CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systemscited by 1
  13. 2026MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systemscited by 1
  14. 2026DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Pathscited by 1
  15. 2026LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoningcited by 1
  16. 2026Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graphcited by 1
  17. 2026Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systemscited by 1
  18. 2026Decoupled Travel Planning with Behavior Forestcited by 1
  19. 2026APWA: A Distributed Architecture for Parallelizable Agentic Workflowscited by 1
  20. 2026Multi-Agent Coordination Adaptation via Structure-Guided Orchestrationcited by 1
  21. 2026FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaborationcited by 1
  22. 2026Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systemscited by 1
  23. 2025Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agentscited by 0
  24. 2026Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Sciencecited by 0
  25. 2026One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queriescited by 0
  26. 2026Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulationcited by 0
  27. 2026Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systemscited by 0
  28. 2026RIFT-Bench: Dynamic Red-teaming For Agentic AI Systemscited by 0
  29. 2026MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systemscited by 0
  30. 2026Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agentscited by 0
  31. 2026What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levelscited by 0
  32. 2026DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaborationcited by 0
  33. 2026ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents
  2. 2026Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
  3. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  4. 2026MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
  5. 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
  6. 2026DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems
  7. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
  8. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs