ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation

ArXi:2603.20513v1 Announce Type: cross LLM-reranking is limited by the top-k documents retrieved by vector similarity, which neither enables contextual query-document token interactions nor captures multimodal relevance distributions. While LLM query reformulation attempts to improve recall by generating improved or additional queries, it is still followed by vector similarity retrieval. We thus propose to address these top-k retrieval stage failures by