The field of intent modeling is experiencing significant growth, with a focus on developing more accurate and effective methods for understanding user intentions in e-commerce and search systems. Recent research has highlighted the importance of incorporating semantic information and multimodal approaches to improve intent recognition. The use of large language models and graph neural networks has shown promise in enhancing recommendation performance and capturing complex user intentions. Noteworthy papers in this area include: SessionIntentBench, which introduces a multimodal benchmark for evaluating intention shift modeling in e-commerce customer behavior. Intent-Aware Neural Query Reformulation, which proposes a robust data pipeline for mining and analyzing buyer query logs to extract fine-grained intent signals. These advancements have the potential to significantly improve the accuracy and effectiveness of intent modeling in e-commerce and search systems, enabling more personalized and relevant recommendations and search results.