GameGPT: Multi-agent Collaborative Framework for Game Development
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development and propose a multi-agent collaborative framework, dubbed GameGPT, to automate game development. While many studies have pinpointed hallucination as a primary roadblock for deploying LLMs in production, we identify another concern: redundancy. Our framework presents a series of methods to mitigate both concerns. These methods include dual collaboration and layered approaches with several in-house lexicons, to mitigate the hallucination and redundancy in the planning, task identification, and implementation phases. Furthermore, a decoupling approach is also introduced to achieve code generation with better precision.
Key facts. Cited by 42 papers in the map (data through 13 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 24 references that are in the map. First posted on arXiv 12 Oct 2023.
Builds on
15 of 24 references.
References · 15
- 2017Attention Is All You Needcited by 60,106
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
- 2020Language Models are Few-Shot Learnerscited by 32,320
- 2022Training language models to follow instructions with human feedbackcited by 15,856
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,072
- 2020Measuring Massive Multitask Language Understandingcited by 7,876
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
- 2022Scaling Instruction-Finetuned Language Modelscited by 3,007
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,693
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,777
- 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,180
- 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,093
3 more
- 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 252
- 2023MindAgent: Emergent Gaming Interactioncited by 88
- 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
Built on by
Citing papers per year: 2023: 2; 2024: 14; 2025: 13; 2026: 13.
42 papers.
Sort:
By area:
- 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 625
- 2025Memory in the Age of AI Agentscited by 291
- 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 236
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 198
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 171
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
- 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 113
- 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
- 2023Experiential Co-Learning of Software-Developing Agentscited by 57
- 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 57
- 2026Code as Agent Harnesscited by 44
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 43
30 more
- 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systemscited by 39
- 2023LARP: Language-Agent Role Play for Open-World Gamescited by 24
- 2024Large Language Models and Video Games: A Preliminary Scoping Reviewcited by 23
- 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
- 2025The FM Agentcited by 21
- 2024Iterative Experience Refinement of Software-Developing Agentscited by 16
- 2024GPT for Games: A Scoping Review (2020-2023)cited by 10
- 2024GPT for Games: An Updated Scoping Review (2020-2024)cited by 10
- 2024Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiencycited by 7
- 2025The Era of Agentic Organization: Learning to Organize with Language Modelscited by 7
- 2025Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systemscited by 4
- 2026GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systemscited by 4
- 2024Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Gamecited by 3
- 2025JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audiencecited by 3
- 2025Co-Saving: Resource Aware Multi-Agent Collaboration for Software Developmentcited by 3
- 2026ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenascited by 3
- 2026UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Developmentcited by 2
- 2024Agent-Driven Automatic Software Improvementcited by 1
- 2025Multi-Agent Game Generation and Evaluation via Audio-Visual Recordingscited by 1
- 2025FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCscited by 1
- 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMscited by 1
- 2026LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuningcited by 1
- 2026Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraintscited by 1
- 2026GameASG-Bench: Benchmarking Autonomous Software Generation for Game Developmentcited by 1
- 2025Communicative Agents for Slideshow Storytelling Video Generation based on LLMscited by 0
- 2026GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generationcited by 0
- 2026RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Modelscited by 0
- 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspectivecited by 0
- 2026Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Riskscited by 0
- 2026Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harnesscited by 0
- 2026Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness6 Oct 2026
- 2026GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development18 Sep 2026
- 2026Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks26 Aug 2026
- 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspective17 Jul 2026
- 2026UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development2 Jul 2026
- 2026RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models17 Jun 2026
- 2026Code as Agent Harness18 May 2026
- 2026GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation27 Apr 2026
- 2026GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems14 Mar 2026
- 2026Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints7 Mar 2026
- 2026ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas4 Feb 2026
- 2026LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning28 Jan 2026
30 more
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents14 Jan 2026
- 2025Memory in the Age of AI Agents15 Dec 2025
- 2025The Era of Agentic Organization: Learning to Organize with Language Models30 Oct 2025
- 2025The FM Agent30 Oct 2025
- 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs7 Sep 2025
- 2025Communicative Agents for Slideshow Storytelling Video Generation based on LLMs1 Sep 2025
- 2025FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs25 Aug 2025
- 2025Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings1 Aug 2025
- 2025Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems22 Jul 2025
- 2025Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development28 May 2025
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges27 Mar 2025
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar 2025
- 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems16 Feb 2025
- 2025JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience28 Jan 2025
- 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents14 Nov 2024
- 2024GPT for Games: An Updated Scoping Review (2020-2024)1 Nov 2024
- 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct 2024
- 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems23 Sep 2024
- 2024Agent-Driven Automatic Software Improvement24 Jun 2024
- 2024Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game16 Jun 2024
- 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun 2024
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways4 Jun 2024
- 2024Iterative Experience Refinement of Software-Developing Agents7 May 2024
- 2024GPT for Games: A Scoping Review (2020-2023)27 Apr 2024
- 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr 2024
- 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges15 Mar 2024
- 2024Large Language Models and Video Games: A Preliminary Scoping Review5 Mar 2024
- 2024Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency29 Feb 2024
- 2023Experiential Co-Learning of Software-Developing Agents28 Dec 2023
- 2023LARP: Language-Agent Role Play for Open-World Games24 Dec 2023
- 2025Memory in the Age of AI Agentscited by 291
- 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 236
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 198
- 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 113
- 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
- 2023Experiential Co-Learning of Software-Developing Agentscited by 57
- 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 57
- 2026Code as Agent Harnesscited by 44
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 43
- 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systemscited by 39
- 2023LARP: Language-Agent Role Play for Open-World Gamescited by 24
- 2025The FM Agentcited by 21
12 most cited of 25 All 25 (JSON)
- 2026Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness6 Oct 2026
- 2026Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks26 Aug 2026
- 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspective17 Jul 2026
- 2026UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development2 Jul 2026
- 2026Code as Agent Harness18 May 2026
- 2026GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems14 Mar 2026
- 2026LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning28 Jan 2026
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents14 Jan 2026
- 2025Memory in the Age of AI Agents15 Dec 2025
- 2025The Era of Agentic Organization: Learning to Organize with Language Models30 Oct 2025
- 2025The FM Agent30 Oct 2025
- 2025Communicative Agents for Slideshow Storytelling Video Generation based on LLMs1 Sep 2025
12 newest of 25 All 25 (JSON)
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 171
- 2024Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Gamecited by 3
- 2026RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Modelscited by 0
- 2026RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models17 Jun 2026
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar 2025
- 2024Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game16 Jun 2024
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
- 2024Large Language Models and Video Games: A Preliminary Scoping Reviewcited by 23
- 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
- 2024GPT for Games: A Scoping Review (2020-2023)cited by 10
- 2024GPT for Games: An Updated Scoping Review (2020-2024)cited by 10
- 2024Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiencycited by 7
- 2025JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audiencecited by 3
- 2026ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenascited by 3
- 2025FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCscited by 1
- 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMscited by 1
- 2026Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraintscited by 1
- 2026GameASG-Bench: Benchmarking Autonomous Software Generation for Game Developmentcited by 1
12 most cited of 13 All 13 (JSON)
- 2026GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development18 Sep 2026
- 2026GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation27 Apr 2026
- 2026Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints7 Mar 2026
- 2026ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas4 Feb 2026
- 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs7 Sep 2025
- 2025FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs25 Aug 2025
- 2025JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience28 Jan 2025
- 2024GPT for Games: An Updated Scoping Review (2020-2024)1 Nov 2024
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways4 Jun 2024
- 2024GPT for Games: A Scoping Review (2020-2023)27 Apr 2024
- 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges15 Mar 2024
- 2024Large Language Models and Video Games: A Preliminary Scoping Review5 Mar 2024
12 newest of 13 All 13 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2026GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
- 2024MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming
- 2023Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game
- 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
- 2026OpenGame: Open Agentic Coding for Games
- 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
- 2026A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?
- 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review