Appendix B Case Study

本文为论文《Search-o1：让推理模型学会边思考边检索》「论文原文」板块的对应章节，按 arXiv 官方全文逐字保留，层级与「中文全文翻译」板块一一对应。

Tables 4, 5, and 6 present examples of outputs from our Search-o1 model on the GPQA, AMC2023, and HotpotQA datasets, respectively. The model-generated search queries are enclosed within <|begin_search_query|> and <|end_search_query|>, while the refined search results are enclosed within <|begin_search_result|> and <|end_search_result|>. We observe that our Reason-in-Documents mechanism provides coherent information that effectively meets the information needs of the model’s current reasoning step and seamlessly integrates with the preceding reasoning process.

Table 4: An example from Search-o1 on GPQA dataset, with special symbols used in the search queries and search results highlighted in green box and blue box, respectively.

Table 5: An example from Search-o1 on AMC2023 dataset, with special symbols used in the search queries and search results highlighted in green box and blue box, respectively.

Table 6: An example from Search-o1 on HotpotQA dataset, with special symbols used in the search queries and search results highlighted in green box and blue box, respectively.