Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded questions, and a Solver, which solves them through internal consistency, where learning proceeds through a continuous self-rewarding process. This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning without relying on ground-truth or human judgments. When using the popular Qwen2.5-VL as the base model, our EvoLMM yields consistent gains upto $\sim$3\% on multimodal math-reasoning benchmarks, including ChartQA, MathVista, and MathVision, using only raw training images. We hope our simple yet effective approach will serve as a solid baseline easing future research in self-improving LMMs in a fully-unsupervised fashion. Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.

翻译：近期大型多模态模型（LMMs）的进展已赋予其卓越的推理与感知能力，但现有训练流程大多仍依赖人工标注数据或外部验证奖励模型，限制了其自主性与可扩展性。本文旨在以完全无监督方式（无需任何标注数据或奖励蒸馏）提升LMM推理能力。为此，我们提出名为EvoLMM的自进化框架，该框架从单一骨干模型实例化两个协同智能体：提案器（Proposer）生成多样化的基于图像的问题，求解器（Solver）通过内部一致性解决这些问题，学习过程通过连续自奖励机制推进。这种动态反馈机制无需依赖真实标注或人工评判，即可同时促进信息性查询的生成与结构化推理的优化。以主流Qwen2.5-VL为基础模型时，仅使用原始训练图像，EvoLMM即可在多模态数学推理基准（包括ChartQA、MathVista和MathVision）上获得约3%的持续性能提升。我们期望这种简洁有效的方法能为未来完全无监督的自进化LMM研究提供稳健基线。代码与模型已开源至https://github.com/mbzuai-oryx/EvoLMM。