Metraipolis › archive › dc_4d62832db024

MegaMem: A Retrieval Solution for Ultra-Large Context Windows — arXiv:2608.22137

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22137
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:17.003Z
SHA-256 of the archived text: 23964ff6182df39c465df315e4d0e6024b695240334e7ffaf9b4775ec91e8fc4
Stable URL of this page: https://metraipolis.com/documento/dc_4d62832db024

How to cite

MegaMem: A Retrieval Solution for Ultra-Large Context Windows — arXiv:2608.22137 — arXiv (en), https://arxiv.org/abs/2608.22137 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d62832db024 (Metraipolis archive dc_4d62832db024, sha256 23964ff6182df39c465df315e4d0e6024b695240334e7ffaf9b4775ec91e8fc4)

BibTeX

@misc{dc4d62832db024,
  title = {MegaMem: A Retrieval Solution for Ultra-Large Context Windows — arXiv:2608.22137},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22137},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d62832db024; sha256 23964ff6182df39c465df315e4d0e6024b695240334e7ffaf9b4775ec91e8fc4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22137. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge is to keep hundreds of millions of tokens searchable while passing only bounded source evidence to the answer model. We introduce MegaMem, a source-resolved dual-view retrieval system that separates semantic access from generation evidence. Distilled records and detailed evidence are searched with original and transformed queries; every distilled hit resolves to an immutable source ID before reciprocal-rank fusion, deduplication, and cross-encoder reranking; and only the highest-ranked detailed evidence within a fixed budget supports generation. Post-answer attribution then identifies which loaded sources support the fixed answer. We evaluate MegaMem on EnterpriseRAG-Bench, which contains more than 500,000 heterogeneous enterprise documents and approximately 650M tokens. MegaMem improves Overall from 68.22 to 82.26 and reaches 86.50 Correctness. These results show that MegaMem supports ultra-large persistent memory while preserving strong answer accuracy under a bounded generation context. By separating searchable memory scale from answer-context size, MegaMem provides a practical path toward accurate retrieval over memories ranging from hundreds of millions to one billion tokens. Our code is available at this https URL xfab-xinyuansong/MegaMem.git.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22137 — 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 2026-10-18T07:37:52.703Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).