# Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents

arXiv: https://arxiv.org/abs/2510.23691 · HTML: https://mlsanity.com/paper/2510.23691/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 59 of its 76 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 59)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)

## Built on by (most cited first, 24 of 24)

- [SIMA 2: A Generalist Embodied Agent for Virtual Worlds](https://mlsanity.com/paper/2512.04797/) (2025)
- [Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.26684/) (2026)
- [OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent](https://mlsanity.com/paper/2601.07779/) (2026)
- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games](https://mlsanity.com/paper/2602.17594/) (2026)
- [Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing](https://mlsanity.com/paper/2601.04575/) (2026)
- [GameVerse: Can Vision-Language Models Learn from Video-based Reflection?](https://mlsanity.com/paper/2603.06656/) (2026)
- [OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics](https://mlsanity.com/paper/2606.09826/) (2026)
- [MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs](https://mlsanity.com/paper/2602.18600/) (2026)
- [Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning](https://mlsanity.com/paper/2605.00347/) (2026)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games](https://mlsanity.com/paper/2607.26712/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [IPR-1: Interactive Physical Reasoner](https://mlsanity.com/paper/2511.15407/) (2025)
- [MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models](https://mlsanity.com/paper/2602.02212/) (2026)
- [Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation](https://mlsanity.com/paper/2605.27134/) (2026)
- [GameWAM: A World Action Model for Video Games](https://mlsanity.com/paper/2608.26200/) (2026)
- [VISTA: A Visual Harness for Reasoning in an Interactive World](https://mlsanity.com/paper/2610.02200/) (2026)
- [Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning](https://mlsanity.com/paper/2512.09706/) (2025)
- [Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play](https://mlsanity.com/paper/2604.17696/) (2026)
- [GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents](https://mlsanity.com/paper/2605.20246/) (2026)
- [GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay](https://mlsanity.com/paper/2609.25001/) (2026)
- [Player-1: Learning to Play from Synthetic Experience](https://mlsanity.com/paper/2610.20584/) (2026)

## Abstract (arXiv)

We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale continual pre-training across heterogeneous domains, including OS, web, and simulation games. Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data. Key techniques include a decaying continual loss to reduce causal confusion and an efficient Sparse-Thinking strategy that balances reasoning depth and inference cost. Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks, is close to the generality of fresh humans in unseen web 3d games, and outperforms GPT-5, Gemini-2.5-Pro, and Claude-4-Sonnet in FPS benchmarks. Scaling results on training-time and test-time confirm that the unified action space sustains improvements when scaled to cross-game and multimodal data. Our results demonstrate that simple, scalable action representations combined with large-scale pre-training provide a promising path toward generalist agents with broad computer-use abilities.