FlyHash 用于 LLM 智能体记忆：实证验证与新应用
FlyHash for LLM Agent Memory: An Empirical Validation and a New Application
AI 导读
一项 arXiv 论文首次将 FlyHash（果蝇嗅觉回路启发的稀疏哈希）应用于 LLM 智能体记忆检索并实证验证。结果显示，在匹配比特数协议下 FlyHash 的质量优势在 10 个种子和 4 个数据集上稳健成立，且在真实智能体记忆相关性标注下依然保持；但在同等比特数下其编码更大、比较更慢，且在常规规模上 HNSW 稠密向量索引优于两种哈希方法。
正文 · 原文
Abstract:Large language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings searched with approximate nearest-neighbor methods. The fruit fly's olfactory circuit computes a locality-sensitive hash of sensory input using a strikingly different mechanism - sparse random projection followed by winner-take-all competition - and prior work (Dasgupta et al., 2017) showed this scheme, dubbed FlyHash, preserves neighbor structure better per bit than conventional random-hyperplane hashing (SimHash) on several benchmarks. We apply FlyHash, to our knowledge for the first time, to LLM agent memory retrieval, and ask three questions a practitioner actually needs answered: does the quality advantage hold under a correctly matched-bit protocol (it does, robustly, across 10 seeds and four datasets spanning two modalities, with one specific, previously undocumented comparison pitfall identified and corrected along the way); does that advantage translate into real memory and latency savings, including against the dense-vector indexing (HNSW) practitioners default to today (no: at equal bits FlyHash's codes are larger and slower to compare than SimHash's, and HNSW dominates both hash methods at ordinary scale; a sparse-set comparison we introduce recovers most but not all of a naive latency gap, leaving hashing's practical case narrower and more specific than the quality result alone implies); and does the advantage survive genuine, non-circular agent-memory relevance labels rather than the nearest-neighbor-by-embedding proxy this literature otherwise relies on (it does). We report all three answers precisely, including the two that narrow rather than flatter the headline result, and release our implementation, a working agent-memory demo, and a full account of the methodological pitfalls we found and corrected.
| Comments: | 19 pages. Code, data and interactive demo: this https URL (archived at this https URL) |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.05791 [cs.AI] |
| (or arXiv:2611.05791v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05791 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chrisogonas Odhiambo [view email]
[v1]
Wed, 4 Nov 2026 00:57:24 UTC (46 KB)
来源：arXiv cs.AI · arxiv.org