mlsanityData to 14 Oct 2026

LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems

arXiv 2504.01963 ↗First posted 13 Mar 2025cs.MA cs.AI cs.CLcited by 10

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

Abstract (arXiv)

This survey investigates foundational technologies essential for developing effective Large Language Model (LLM)-based multi-agent systems. Aiming to answer how best to optimize these systems for collaborative, dynamic environments, we focus on four critical areas: Architecture, Memory, Planning, and Technologies/Frameworks. By analyzing recent advancements and their limitations - such as scalability, real-time response challenges, and agent coordination constraints, we provide a detailed view of the technological landscape. Frameworks like the Mixture of Agents architecture and the ReAct planning model exemplify current innovations, showcasing improvements in role assignment and decision-making. This review synthesizes key strengths and persistent challenges, offering practical recommendations to enhance system scalability, agent collaboration, and adaptability. Our findings provide a roadmap for future research, supporting the creation of robust, efficient multi-agent systems that advance both individual agent performance and collective system resilience.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 27 of its 27 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

27 of 27 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  2. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun
  3. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents5 Mar
  4. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?28 Feb
  5. 2024LLM Multi-Agent Systems: Challenges and Open Problems5 Feb
  6. 2024More Agents Is All You Need3 Feb
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  9. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  6. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  7. 2024Large Language Models: A Surveycited by 525
  8. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 140
  9. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  10. 2024RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agentscited by 80
  11. 2023RET-LLM: Towards a General Read-Write Memory for Large Language Modelscited by 64
  12. 2023ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Modelscited by 43
5 more
  1. 2024When Large Language Models Meet Vector Databases: A Surveycited by 39
  2. 2024On the Limitations of Large Language Models (LLMs): False Attributioncited by 13
  3. 2024A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graphcited by 8
  4. 2024Re-Thinking Process Mining in the AI-Based Agents Eracited by 5
  5. 2024A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisitioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  3. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  4. 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
  5. 2025Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligencecited by 8
  6. 2026Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimizationcited by 3
  7. 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Modelscited by 2
  8. 2026Rethinking Agentic Reinforcement Learning In Large Language Modelscited by 1
  9. 2026When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systemscited by 1
  10. 2026Agentic Frameworks for Reasoning Tasks: An Empirical Studycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
  2. 2024Practical Considerations for Agentic LLM Systems
  3. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  4. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
  5. 2025Modeling Response Consistency in Multi-Agent LLM Systems: A Comparative Analysis of Shared and Separate Context Approaches
  6. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  7. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
  8. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead