EvoLMM：具有连续奖励的自进化大型多模态模型
EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards
AI总结：
提出EvoLMM框架，通过单个骨干模型实例化提议者和求解者两个协作智能体，利用连续自奖励过程无监督地提升LMM推理能力，在ChartQA等基准上取得约3%的提升。
摘要：
近年来，大型多模态模型（LMMs）的进展实现了令人印象深刻的推理和感知能力，但大多数现有训练流程仍依赖于人工策划的数据或外部验证的奖励模型，限制了其自主性和可扩展性。在这项工作中，我们致力于以纯无监督方式（无需任何标注数据或奖励蒸馏）提升LMM的推理能力。为此，我们提出了一个名为EvoLMM的自进化框架，该框架从单个骨干模型实例化两个协作智能体：提议者（Proposer），生成多样化的、基于图像的问题；以及求解者（Solver），通过内部一致性解决这些问题，学习过程通过连续的自奖励机制进行。这种动态反馈促进了信息性查询的生成和结构化推理的改进，而无需依赖真实标签或人工判断。当使用流行的Qwen2.5-VL作为基础模型时，我们的EvoLMM在多模态数学推理基准（包括ChartQA、MathVista和MathVision）上取得了约3%的持续提升，仅使用原始训练图像。我们希望这种简单而有效的方法能成为一个坚实的基线，促进未来在完全无监督方式下自我改进LMM的研究。我们的代码和模型可在该https URL获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
