Metraipolis › archive › dc_17f42928afd7
Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants — arXiv:2611.02612
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02612
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:48:26.663Z
- SHA-256 of the archived text
7e201d59045cff98173154715942526adc3c9e178ce4300c1b7427e8dd9ec8dc- Stable URL of this page
https://metraipolis.com/documento/dc_17f42928afd7
How to cite
Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants — arXiv:2611.02612 — arXiv (en), https://arxiv.org/abs/2611.02612 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_17f42928afd7 (Metraipolis archive dc_17f42928afd7, sha256 7e201d59045cff98173154715942526adc3c9e178ce4300c1b7427e8dd9ec8dc)
BibTeX
@misc{dc17f42928afd7,
title = {Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants — arXiv:2611.02612},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02612},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_17f42928afd7; sha256 7e201d59045cff98173154715942526adc3c9e178ce4300c1b7427e8dd9ec8dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02612. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Enterprise conversational systems require memory to personalize interactions, retain information across sessions, and maintain conversational coherence. At enterprise scale, however, memory must not only retrieve relevant information accurately but also provide it efficiently to the answer-generation model. Existing memory systems face a trade-off between retrieval accuracy and context efficiency. Retrieving more context can improve recall but increases inference cost and latency. We present Scalaris, a scalable enterprise memory architecture that addresses this trade-off through a unified long-term and short-term memory design. We propose that user interactions and assistant responses possess distinct characteristics and roles in a conversation: user interactions capture evolving knowledge about the user and provide value across sessions, whereas assistant responses must be stored efficiently so that only information relevant to the current query is retrieved. We therefore treat them separately and support each with specialized representations and ingestion/retrieval pipelines. Scalaris reaches 92.2 % accuracy on LongMemEval-S and 90.77 % on LoCoMo using Qwen3-32B, state-of-the-art results on both benchmarks, while supplying the answer-generation model with approximately 10 times fewer retrieved context tokens than Hindsight, a leading memory system for conversational AI. When integrated with our proprietary closed-source AI assistants, Scalaris improved overall response quality by 36 %. Together, these results establish Scalaris as a cost-effective framework for building scalable, personalized conversational AI systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02612 — 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 2026-11-03T10:39:50.585Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).