跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 19 天前AI 評分43

FlyHash 用於 LLM 智能體記憶:實證驗證與新應用

FlyHash for LLM Agent Memory: An Empirical Validation and a New Application

AI 導讀

FlyHash 用於 LLM 智能體記憶檢索,在位元數匹配及真實相關性標籤下,均比 SimHash 更能保留鄰近結構。這項優勢在 10 個隨機種子及涵蓋兩種模態的四個數據集上成立,但一般規模下 FlyHash 沒有實際記憶體或延遲優勢,HNSW 的表現更佳。研究同時發布實作及可運作的智能體記憶示範。

正文

Published on Nov 4

Authors:

Abstract

FlyHash, a fruit-fly-inspired locality-sensitive hashing method, improves neighbor-structure preservation over SimHash for large language model agent memory retrieval under matched-bit protocols and genuine relevance labels, but it does not provide practical memory or latency advantages over SimHash or HNSW at ordinary scale.

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.

View arXiv page View PDF Project page GitHub 1 Add to collection

Get this paper in your agent:

hf papers read 2611.05791

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.05791 in a model README.md to link it from this page.

Datasets citing this paper 1

pranamhan/agent-memory-v1

Viewer •

Updated about 22 hours ago

•

6.15k

Spaces citing this paper 1

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co