SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917347807199232 |
|---|---|
| author | Derehag, Jesper Calva, Carlos Ghiurau, Timmy |
| author_facet | Derehag, Jesper Calva, Carlos Ghiurau, Timmy |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15599 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval Derehag, Jesper Calva, Carlos Ghiurau, Timmy Machine Learning 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. |
| title | SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.15599 |