The field of natural language processing is moving towards more advanced and specialized language models, with a focus on improving the ability of large language models to browse the web and process domain-specific information. Researchers are exploring new methods for fine-tuning and evaluating language models, particularly for Classical Chinese and other non-English languages. The development of new benchmarks and evaluation datasets is also a key area of focus, with the goal of improving the performance and accuracy of language models in real-world applications. Notable papers in this area include: MTCSC, which proposes a retrieval-augmented iterative refinement framework for Chinese spelling correction, significantly outperforming current approaches. BrowseComp-ZH, a benchmark for evaluating the web browsing ability of large language models in Chinese, which demonstrates the considerable difficulty of this task and the need for further research. WenyanGPT, a large language model specifically designed for Classical Chinese tasks, which achieves state-of-the-art results on various tasks and provides a comprehensive solution for Classical Chinese language processing.