# Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning

arXiv: https://arxiv.org/abs/2505.13886 · HTML: https://mlsanity.com/paper/2505.13886/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning](https://mlsanity.com/paper/2105.04165/) (2021)
- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model](https://mlsanity.com/paper/2312.11370/) (2023)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models](https://mlsanity.com/paper/2406.17294/) (2024)
- [MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models](https://mlsanity.com/paper/2409.00147/) (2024)
- [Distill Visual Chart Reasoning Ability from LLMs to MLLMs](https://mlsanity.com/paper/2410.18798/) (2024)
- [LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning](https://mlsanity.com/paper/2409.12929/) (2024)
- [ING-VP: MLLMs cannot Play Easy Vision-based Games Yet](https://mlsanity.com/paper/2410.06555/) (2024)
- [VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models](https://mlsanity.com/paper/2411.09105/) (2024)

## Built on by (most cited first, 30 of 32)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025)
- [MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods](https://mlsanity.com/paper/2601.21821/) (2026)
- [Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks](https://mlsanity.com/paper/2511.15065/) (2025)
- [MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data](https://mlsanity.com/paper/2603.09206/) (2026)
- [InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling](https://mlsanity.com/paper/2508.08636/) (2025)
- [Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models](https://mlsanity.com/paper/2601.19834/) (2026)
- [Play to Generalize: Learning to Reason Through Game Play](https://mlsanity.com/paper/2506.08011/) (2025)
- [DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing](https://mlsanity.com/paper/2602.12205/) (2026)
- [UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing](https://mlsanity.com/paper/2602.02437/) (2026)
- [AI Can Learn Scientific Taste](https://mlsanity.com/paper/2603.14473/) (2026)
- [Vero: An Open RL Recipe for General Visual Reasoning](https://mlsanity.com/paper/2604.04917/) (2026)
- [SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning](https://mlsanity.com/paper/2601.04809/) (2026)
- [DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning](https://mlsanity.com/paper/2602.16742/) (2026)
- [SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2602.20901/) (2026)
- [MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization](https://mlsanity.com/paper/2510.08540/) (2025)
- [PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs](https://mlsanity.com/paper/2512.14944/) (2025)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning](https://mlsanity.com/paper/2607.20166/) (2026)
- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning](https://mlsanity.com/paper/2607.19790/) (2026)
- [Beacon: Knowing When and How to Perform Agentic Visual Reasoning](https://mlsanity.com/paper/2607.28595/) (2026)
- [Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement](https://mlsanity.com/paper/2606.12886/) (2026)
- [The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping](https://mlsanity.com/paper/2608.06361/) (2026)
- [Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments](https://mlsanity.com/paper/2609.32208/) (2026)
- [ReSight-SMC: Two-Stage Power Sampling via Island SMC with Visual Scouts](https://mlsanity.com/paper/2609.34905/) (2026)
- [VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning](https://mlsanity.com/paper/2610.10782/) (2026)

## Abstract (arXiv)

Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underexplored, limiting the exploration and learning of Vision Language Models (VLMs) through RL. We find video games inherently provide rich visual elements and mechanics that are easy to verify. To fully use the multimodal and verifiable reward in video games, we propose Game-RL, constructing diverse game tasks for RL training to boost VLMs general reasoning ability. To obtain training data, we propose Code2Logic, a novel approach that adapts game code to synthesize game reasoning task data, thus obtaining the GameQA dataset of 30 games and 158 tasks with controllable difficulty gradation. Unexpectedly, RL training solely on GameQA enables multiple VLMs to achieve performance improvements across 7 diverse vision-language benchmarks, demonstrating the value of Game-RL for enhancing VLMs' general reasoning. Furthermore, this suggests that video games may serve as valuable scenarios and resources to boost general reasoning abilities. Our code, dataset and models are available at the GitHub repository.