基本信息
- 来源: arxiv
- 原始来源: https://arxiv.org/abs/2603.15599v1
- 作者: Jesper Derehag, Carlos Calva, Timmy Ghiurau
- 分类: cs.LG
- 论文时间: 2026-03-16T17:53:21Z
- 论文 PDF: https://arxiv.org/pdf/2603.15599v1.pdf
来源摘要/节选
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. Oracle analysis on two benchmarks identifies a compilation bottleneck: retrieval recall reaches 98.6%, but without intelligent ranking only 22.5% of gold evidence survives truncation to the token budget. With score-adaptive truncation and no per-dataset tuning, SmartSearch achieves 93.5% on LoCoMo and 88.4% on LongMemEval-S, exceeding all known memory systems under the same evaluation protocol on both benchmarks while using 8.5x fewer tokens than full-context baselines.
来源说明
当前只保存了官方论文摘要，不代表论文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据，不包含基于旧正文或缺失原文的扩展推断。