mlsanityData to 7 Oct 2026

Large Language Models as Agents in Two-Player Games

arXiv 2402.08078 ↗First posted 12 Feb 2024cs.CL cs.LGcited by 10

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

also in 1 more
Abstract (arXiv)

By formally defining the training processes of large language models (LLMs), which usually encompasses pre-training, supervised fine-tuning, and reinforcement learning with human feedback, within a single and unified machine learning paradigm, we can glean pivotal insights for advancing LLM technologies. This position paper delineates the parallels between the training methods of LLMs and the strategies employed for the development of agents in two-player games, as studied in game theory, reinforcement learning, and multi-agent systems. We propose a re-conceptualization of LLM learning processes in terms of agent learning in language-based games. This framework unveils innovative perspectives on the successes and challenges in LLM development, offering a fresh understanding of addressing alignment issues among other strategic considerations. Furthermore, our two-player game approach sheds light on novel data preparation and machine learning techniques for training LLMs.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 64 of its 90 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

64 of 90 references.

References · 64

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2017Deep reinforcement learning from human preferencescited by 3,846
  11. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  12. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
38 more
  1. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  2. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  5. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  6. 2018World Modelscited by 1,444
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  10. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  11. 2022Red Teaming Language Models with Language Modelscited by 983
  12. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  13. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  14. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  15. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  16. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  17. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  18. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  19. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  20. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
  21. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  22. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  23. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  24. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  25. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 377
  26. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  27. 2022Self-critiquing models for assisting human evaluatorscited by 372
  28. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 366
  29. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  30. 2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemblecited by 297
  31. 2023Large Language Model Unlearningcited by 288
  32. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  33. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  34. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  35. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
  36. 2022Can language models learn from explanations in context?cited by 248
  37. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  38. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  3. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  4. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
  5. 2025Seed-X: Building Strong Multilingual Translation LLM with 7B Parameterscited by 21
  6. 2024COMMA: A Communicative Multimodal Multi-Agent Benchmarkcited by 12
  7. 2026Interactive Critique-Revision Training for Reliable Structured LLM Generationcited by 2
  8. 2026LLM Active Alignment: A Nash Equilibrium Perspectivecited by 0
  9. 2026LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Gamescited by 0
  10. 2026Direct Self-Evolving Optimization: Evolving LLMs without Challenger Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Aligning Agents like Large Language Models
  2. 2024A Survey on Large Language Model-Based Game Agents
  3. 2025Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs
  4. 2025Playing games with Large language models: Randomness and strategy
  5. 2026Rethinking Agentic Reinforcement Learning In Large Language Models
  6. 2025Language-Driven Coordination and Learning in Multi-Agent Simulation Environments
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  8. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information