LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval

ArXi:2510.13217v2 Announce Type: replace-cross Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning over the query-document relation rather than relying on surface vocabulary or topical similarity. The standard recipe - a cheap embedding-based retriever followed by an LLM verifier - works only when the embedding model places the right documents in its top-k, an assumption that recent reasoning-intensive IR benchmarks show often fails to hold even for SOTA embedding models.