Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building deep research systems. We revisit it by pairing BM25 with frontier LLMs that have better reasoning and tool-use abilities. To support researchers asking the same question, we introduce Pi-Serini, a search agent equipped with three tools for retrieving, browsing, and reading documents. Our results show that, on BrowseComp-Plus, a well-configured lexical retriever with sufficient retrieval depth can support effective deep research when paired with more capable LLMs. Specifically, Pi-Serini with gpt-5.5 achieves 83.1% answer accuracy and 94.7% surfaced evidence recall, outperforming released search agents that use dense retrievers. Controlled ablations further show that BM25 tuning improves answer accuracy by 18.0% and surfaced evidence recall by 11.1% over the default BM25 setting, while increasing retrieval depth further improves surfaced evidence recall by 25.3% over the shallow-retrieval setting. Source code is available at https://github.com/justram/pi-serini.

翻译：随着大语言模型在代理循环中能力不断增强，词汇检索器是否足以胜任？这一疑问在构建深度研究系统时自然浮现。我们通过将 BM25 与具备更强推理和工具使用能力的前沿大语言模型配对使用，重新审视了该问题。为支持提出同样疑问的研究人员，我们推出了 Pi-Serini——一个配备文档检索、浏览和阅读三种工具的搜索代理。结果表明，在 BrowseComp-Plus 数据集上，配置得当且检索深度足够的词汇检索器，在与更强的大语言模型配合时，能够支持有效的深度研究。具体而言，使用 gpt-5.5 的 Pi-Serini 实现了 83.1% 的答案准确率和 94.7% 的表面证据召回率，性能优于已发布的使用稠密检索器的搜索代理。控制消融实验进一步表明，与默认 BM25 设置相比，BM25 调优将答案准确率提升了 18.0%，表面证据召回率提升了 11.1%；而增加检索深度相较于浅层检索设置，进一步将表面证据召回率提升了 25.3%。源代码已发布于 https://github.com/justram/pi-serini。