With the rapid growth of e-commerce, exploring general representations rather than task-specific ones has attracted increasing attention. Although recent multimodal large language models (MLLMs) have driven significant progress in product understanding, they are typically employed as feature extractors that implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. Therefore, we argue that leveraging the reasoning capabilities of MLLMs to explicitly model fine-grained product attributes holds significant potential. Nevertheless, achieving this goal remains non-trivial due to several key challenges: (i) long-context reasoning tends to dilute the model's attention to salient information in the raw input; (ii) supervised fine-tuning (SFT) primarily encourages rigid imitation, limiting the exploration of effective reasoning strategies; and (iii) fine-grained details are progressively attenuated during forward propagation. To address these issues, we propose MOON3.0, the first reasoning-aware MLLM-based model for product representation learning. Our method (1) employs a multi-head modality fusion module to adaptively integrate raw signals; (2) incorporates a joint contrastive and reinforcement learning framework to autonomously explore more effective reasoning strategies; and (3) introduces a fine-grained residual enhancement module to progressively preserve local details throughout the network. Additionally, we release a large-scale multimodal e-commerce benchmark MBE3.0. Experimentally, our model demonstrates state-of-the-art zero-shot performance across various downstream tasks on both our benchmark and public datasets.

翻译：随着电子商务的快速发展，探索通用表示而非任务特定表示日益受到关注。尽管近期多模态大语言模型（MLLMs）在商品理解领域取得了显著进展，但它们通常被用作特征提取器，将商品信息隐式编码为全局嵌入，从而限制了捕获细粒度属性的能力。因此，我们认为利用MLLMs的推理能力显式建模细粒度商品属性具有重要潜力。然而，实现这一目标仍面临若干关键挑战：（i）长上下文推理容易稀释模型对原始输入中显著信息的注意力；（ii）监督微调（SFT）主要鼓励机械模仿，限制了有效推理策略的探索；（iii）前向传播过程中细粒度细节逐渐衰减。为解决这些问题，我们提出MOON3.0——首个基于推理感知MLLM的商品表示学习模型。我们的方法：（1）采用多头模态融合模块自适应整合原始信号；（2）引入联合对比学习与强化学习框架，自主探索更有效的推理策略；（3）提出细粒度残差增强模块，在网络中逐步保留局部细节。此外，我们发布了大规模多模态电子商务基准MBE3.0。实验表明，我们的模型在自身基准与公开数据集上的多项下游任务中均展现出最先进的零样本性能。