Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

ArXi:2605.10848v1 Announce Type: cross Does a lexical retriever suffice as large language models (LLMs) become 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 researchers asking the same question, we