mlsanityData to 7 Oct 2026

LLM-based multi-agent poetry generation in non-cooperative environments

arXiv 2409.03659 ↗First posted 5 Sep 2024cs.CLcited by 15

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

Abstract (arXiv)

Despite substantial progress of large language models (LLMs) for automatic poetry generation, the generated poetry lacks diversity while the training process differs greatly from human learning. Under the rationale that the learning process of the poetry generation systems should be more human-like and their output more diverse and novel, we introduce a framework based on social learning where we emphasize non-cooperative interactions besides cooperative interactions to encourage diversity. Our experiments are the first attempt at LLM-based multi-agent systems in non-cooperative environments for poetry generation employing both TRAINING-BASED agents (GPT-2) and PROMPTING-BASED agents (GPT-3 and GPT-4). Our evaluation based on 96k generated poems shows that our framework benefits the poetry generation process for TRAINING-BASED agents resulting in 1) a 3.0-3.7 percentage point (pp) increase in diversity and a 5.6-11.3 pp increase in novelty according to distinct and novel n-grams. The generated poetry from TRAINING-BASED agents also exhibits group divergence in terms of lexicons, styles and semantics. PROMPTING-BASED agents in our framework also benefit from non-cooperative environments and a more diverse ensemble of models with non-homogeneous agents has the potential to further enhance diversity, with an increase of 7.0-17.5 pp according to our experiments. However, PROMPTING-BASED agents show a decrease in lexical diversity over time and do not exhibit the group-based divergence intended in the social network. Our paper argues for a paradigm shift in creative tasks such as automatic poetry generation to include social learning processes (via LLM-based agent modeling) similar to human interaction.

Key facts. Cited by 15 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 65 of its 93 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

65 of 93 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  2. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  3. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 61

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  8. 2024Mixtral of Expertscited by 1,785
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  11. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  12. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
38 more
  1. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  2. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  3. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  4. 2022A Contrastive Framework for Neural Text Generationcited by 224
  5. 2022Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Modelscited by 218
  6. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 153
  7. 2019Queens are Powerful too: Mitigating Gender Bias in Dialogue Generationcited by 152
  8. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  9. 2022AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuningcited by 137
  10. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  11. 2020Evaluating the Evaluation of Diversity in Natural Language Generationcited by 127
  12. 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
  13. 2020Towards Controllable Biases in Language Generationcited by 112
  14. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  15. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  16. 2023AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Modelscited by 84
  17. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  18. 2022Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writingcited by 71
  19. 2023Machine Culturecited by 55
  20. 2023Controlled Text Generation via Language Model Arithmeticcited by 51
  21. 2021Structural Adapters in Pretrained Language Models for AMR-to-text Generationcited by 48
  22. 2023Fusing Models with Complementary Expertisecited by 45
  23. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  24. 2023Click: Controllable Text Generation with Sequence Likelihood Contrastive Learningcited by 41
  25. 2020The Adapter-Bot: All-In-One Controllable Conversational Modelcited by 38
  26. 2023Blind Judgement: Agent-Based Supreme Court Modelling With GPTcited by 37
  27. 2018Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhymecited by 35
  28. 2023The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agentscited by 30
  29. 2024Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLMcited by 26
  30. 2022ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Modelscited by 25
  31. 2022Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Featurescited by 24
  32. 2023CALYPSO: LLMs as Dungeon Masters' Assistantscited by 23
  33. 2016Chinese Poetry Generation with Planning based Neural Networkcited by 22
  34. 2023Quantifying the Impact of Large Language Models on Collective Opinion Dynamicscited by 22
  35. 2020MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Spacecited by 17
  36. 2022Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policycited by 17
  37. 2024Evaluating Diversity in Automatic Poetry Generationcited by 17
  38. 2020AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generationcited by 15

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 8.

15 papers.

Sort:

By area:

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  2. 2025Agentic Large Language Models, a surveycited by 105
  3. 2024How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMscited by 23
  4. 2025A Cognitive Writing Perspective for Constrained Long-Form Text Generationcited by 14
  5. 2025LiTransProQA: an LLM-based Literary Translation evaluation metric with Professional Question Answeringcited by 10
  6. 2025Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Abilitycited by 10
  7. 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Modelscited by 2
  8. 2025ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluationcited by 1
  9. 2026On the Creativity of AI Agentscited by 1
  10. 2026How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Themcited by 1
  11. 2026Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translationcited by 1
  12. 2026Instruction-Guided Poetry Generation in Arabic and Its Dialectscited by 1
3 more
  1. 2026System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5cited by 1
  2. 2026LLMs Should Incorporate Explicit Mechanisms for Human Empathycited by 0
  3. 2026Exploring LLMs for South Asian Music Understanding and Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
  2. 2025Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models
  3. 2025Creativity in LLM-based Multi-Agent Systems: A Survey
  4. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
  5. 2023Adapting LLM Agents with Universal Feedback in Communication
  6. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  7. 2025Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
  8. 2024Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities