NaviRank: LLM-Informed Latent Space Navigation Enhances Reasoning-Intensive Information Retrieval
Abstract
AbstractRetrieve-then-rerank pipelines restrict large language models (LLMs) to a fixed top-k candidate set, making their reasoning ability fundamentally limited by the recall ceiling of the first-stage dense retriever. On reasoning-intensive retrieval, we make two observations: first, relevant documents missed by dense top-k retrieval are frequently reachable within a few hops on the native approximate nearest neighbor (ANN) graph; second, LLM relevance judgments can identify high-yield anchors whose neighborhoods contain these missed documents. Based on these findings, we propose NaviRank, an LLM-guided navigation framework that performs greedy expansion over the HNSW graph: it uses highly parallel pointwise LLM judgments to steer anchor selection and local expansion, followed by listwise calibration for final ranking. Experiments on BRIGHT show that NaviRank achieves 27.0 NDCG@10, while establishing the strongest accuracy–efficiency Pareto frontier in both token usage and latency among all evaluated methods.