Metraipolis › archive › dc_46337b5b91ee

FlyHash for LLM Agent Memory: An Empirical Validation and a New Application — arXiv:2611.05791

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05791
License (as archived)
CC0-1.0
Archived
2026-11-05T18:16:46.899Z
SHA-256 of the archived text
e68e8dba2200d3f23c0d1bcd51bd4540777492b84cd2ccf1dbcf9eaee87b5ab7
Stable URL of this page
https://metraipolis.com/documento/dc_46337b5b91ee

How to cite

FlyHash for LLM Agent Memory: An Empirical Validation and a New Application — arXiv:2611.05791 — arXiv (en), https://arxiv.org/abs/2611.05791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46337b5b91ee (Metraipolis archive dc_46337b5b91ee, sha256 e68e8dba2200d3f23c0d1bcd51bd4540777492b84cd2ccf1dbcf9eaee87b5ab7)
BibTeX
@misc{dc46337b5b91ee,
  title = {FlyHash for LLM Agent Memory: An Empirical Validation and a New Application — arXiv:2611.05791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46337b5b91ee; sha256 e68e8dba2200d3f23c0d1bcd51bd4540777492b84cd2ccf1dbcf9eaee87b5ab7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05791 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:12:48.999Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).