mlsanityData to 7 Oct 2026

Creativity in LLM-based Multi-Agent Systems: A Survey

arXiv 2505.21116 ↗First posted 27 May 2025cs.HC cs.AI cs.CLcited by 23

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

Abstract (arXiv)

Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide comprehensive overviews of MAS infrastructures, they largely overlook the dimension of creativity, including how novel outputs are generated and evaluated, how creativity informs agent personas, and how creative workflows are coordinated. This is the first survey dedicated to creativity in MAS. We focus on text and image generation tasks, and present: (1) a taxonomy of agent proactivity and persona design; (2) an overview of generation techniques, including divergent exploration, iterative refinement, and collaborative synthesis, as well as relevant datasets and evaluation metrics; and (3) a discussion of key challenges, such as inconsistent evaluation standards, insufficient bias mitigation, coordination conflicts, and the lack of unified benchmarks. This survey offers a structured framework and roadmap for advancing the development, evaluation, and standardization of creative MAS.

Key facts. Cited by 23 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 66 of its 128 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

66 of 128 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Self-Resource Allocation in Multi-Agent LLM Systems2 Apr
  2. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar
  3. 2025Between Puppet and Actor: Reframing Authorship in this Age of AI Agents25 Jan
  4. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  5. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks18 Dec
  6. 2024Creative Agents: Simulating the Systems Model of Creativity with Generative Agents26 Nov
  7. 2024MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming25 Oct
  8. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
  9. 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures5 Oct
  10. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  11. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul

Other references · 55

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  6. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  7. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  10. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  11. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  12. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
38 more
  1. 2020Artificial Intelligence, Values and Alignmentcited by 443
  2. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  3. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  4. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  5. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  6. 2024MARG: Multi-Agent Review Generation for Scientific Paperscited by 98
  7. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 89
  8. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  9. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  10. 2024LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Playcited by 65
  11. 2024Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent Systemcited by 63
  12. 2024Agents' Room: Narrative Generation through Multi-step Collaborationcited by 57
  13. 2024Lean Copilot: Large Language Models as Copilots for Theorem Proving in Leancited by 52
  14. 2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactionscited by 50
  15. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
  16. 2024AI-Augmented Brainwriting: Investigating the use of LLMs in group ideationcited by 43
  17. 2024Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinkingcited by 43
  18. 2024Towards audio language modeling -- an overviewcited by 40
  19. 2023CoQuest: Exploring Research Question Co-Creation with an LLM-based Agentcited by 34
  20. 2025AI Idea Bench 2025: AI Research Idea Generation Benchmarkcited by 33
  21. 2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writerscited by 32
  22. 2024Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Taskscited by 28
  23. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  24. 2024CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysiscited by 26
  25. 2024StoryVerse: Towards Co-authoring Dynamic Plot with LLM-based Character Simulation via Narrative Planningcited by 20
  26. 2023DesignGPT: Multi-Agent Collaboration in Designcited by 16
  27. 2024Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debatecited by 16
  28. 2024Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debatescited by 15
  29. 2024Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflowcited by 13
  30. 2025Beyond Code Generation: LLM-supported Exploration of the Program Design Spacecited by 13
  31. 2024Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmascited by 12
  32. 2025One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humorcited by 12
  33. 2022A Collaborative, Interactive and Context-Aware Drawing Agent for Co-Creative Designcited by 10
  34. 2022Creative Wand: A System to Study Effects of Communications in Co-Creative Settingscited by 9
  35. 2024RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Educationcited by 7
  36. 2024MAxPrototyper: A Multi-Agent Generation System for Interactive User Interface Prototypingcited by 6
  37. 2025The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translationcited by 5
  38. 2021Resource allocation in dynamic multiagent systemscited by 4

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 20.

23 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. 2026AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agentcited by 12
  3. 2025BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generationcited by 10
  4. 2026TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Codecited by 6
  5. 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learningcited by 6
  6. 2026When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systemscited by 3
  7. 2026TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric sciencecited by 2
  8. 2026ViviDoc: Generating Interactive Documents through Human-Agent Collaborationcited by 2
  9. 2026OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generationcited by 2
  10. 2025MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignmentcited by 1
  11. 2026TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Taskscited by 1
  12. 2026On the Creativity of AI Agentscited by 1
11 more
  1. 2026Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translationcited by 1
  2. 2026Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimizationcited by 1
  3. 2026Ex Ante Evaluation of AI-Induced Idea Diversity Collapsecited by 1
  4. 2026Multi-Agent Coordination Adaptation via Structure-Guided Orchestrationcited by 1
  5. 2026AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculumcited by 0
  6. 2026Anchorless Diversification for Parallel LLM Ideationcited by 0
  7. 2026Nonuniformity Principle in Human-AI Coworkingcited by 0
  8. 2026SGA: Plug&Play Geometric Verification for Educational Video Synthesiscited by 0
  9. 2026ADE: Agentic Data Evolution Framework for Human-Centered Objectivescited by 0
  10. 2026A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attackscited by 0
  11. 2026Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  2. 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
  3. 2026Multi-agent AI systems outperform human teams in creativity
  4. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration
  5. 2025The Spark Effect: On Engineering Creative Diversity in Multi-Agent AI Systems
  6. 2025Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
  7. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  8. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems