AI RESEARCH
SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
arXiv CS.LG
•
ArXi:2603.15599v1 Announce Type: new Recent conversational memory systems invest heavily in LLM-based structuring at ingestion time and learned retrieval policies at query time. We show that neither is necessary. SmartSearch retrieves from raw, unstructured conversation history using a fully deterministic pipeline: NER-weighted substring matching for recall, rule-based entity discovery for multi-hop expansion, and a CrossEncoder+ColBERT rank fusion stage -- the only learned component -- running on CPU in ~650ms.