paper-with-me

Papers

SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval

2026-03-16 · Jesper Derehag, Carlos Calva, Timmy Ghiurau arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.15599

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SmartSearch: Process Reward-Guided Query Refinement for Search Agents

2026-01-08 · Tongyu Wen, Guanting Dong, Zhicheng Dou arxiv

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoni…

Information Retrieval

Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

2026-05-28 · ZhiShu Jiang, Haibo Liu, Xin Shen, Guanqiang QI 외 arxiv

Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in bui…

The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory

2026-08-24 · Qi Feng, Chris Ding, Jicong Fan arxiv

Long-term language-model agents accumulate memories across interactions, but their retrievers typically do not accumulate retrieval experience. Semantic retrieval is efficient, but embedding similarity does not always re…

Semantic Retrieval

Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents

2026-03-24 · Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo 외 arxiv

Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typically processed with the same computationa…

Semantic XPath: Structured Agentic Memory Access for Conversational AI

2026-03-01 · Yifan Simon Liu, Ruifan Wu, Liam Gallagher, Jiazhou Liang 외 arxiv

Conversational AI (ConvAI) agents increasingly maintain structured memory to support long-term, task-oriented interactions. In-context memory approaches append the growing history to the model input, which scales poorly …