Game-Theoretic Lens on LLM-based Multi-Agent Systems
On the map: LLM reasoning → Reasoning for agents, planning and code
also in 1 more
Abstract (arXiv)
Large language models (LLMs) have demonstrated strong reasoning, planning, and communication abilities, enabling them to operate as autonomous agents in open environments. While single-agent systems remain limited in adaptability and coordination, recent progress has shifted attention toward multi-agent systems (MAS) composed of interacting LLMs that pursue cooperative, competitive, or mixed objectives. This emerging paradigm provides a powerful testbed for studying social dynamics and strategic behaviors among intelligent agents. However, current research remains fragmented and lacks a unifying theoretical foundation. To address this gap, we present a comprehensive survey of LLM-based multi-agent systems through a game-theoretic lens. By organizing existing studies around the four key elements of game theory: players, strategies, payoffs, and information, we establish a systematic framework for understanding, comparing, and guiding future research on the design and analysis of LLM-based MAS.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 41 of its 57 references that are in the map. First posted on arXiv 21 Jan 2026.
Builds on
41 of 57 references.
Closest ancestors · 11
Same direction, newest first
- 2025MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs17 Oct
- 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution31 Jul
- 2025Reasoning and Behavioral Equilibria in LLM-Nash Games: From Mindsets to Actions10 Jul
- 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning30 Jun
- 2025DABstep: Data Agent Benchmark for Multi-step Reasoning30 Jun
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar
- 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?12 Sep
- 2024GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents7 Jun
- 2024Self-playing Adversarial Language Game Enhances LLM Reasoning16 Apr
- 2024GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations19 Feb
- 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
Other references · 30
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
- 2023GAIA: a benchmark for General AI Assistantscited by 1,084
- 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
- 2023ChatDev: Communicative Agents for Software Developmentcited by 893
- 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
- 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
- 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
18 more
- 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
- 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
- 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
- 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 140
- 2024Emergent social conventions and collective bias in LLM populationscited by 115
- 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 112
- 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 97
- 2024PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Taskscited by 78
- 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 73
- 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 55
- 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
- 2025AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Marketscited by 23
- 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
- 2025Risk Analysis Techniques for Governed LLM-based Multi-Agent Systemscited by 16
- 2025FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domaincited by 8
- 2025FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awarenesscited by 6
- 2024Explaining Decisions of Agents in Mixed-Motive Gamescited by 4
- 2025Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Gamescited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios
- 2024A Survey on Large Language Model-Based Game Agents
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
- 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
- 2026Competition and Cooperation of LLM Agents in Games
- 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
- 2024WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis
- 2025Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs