Metraipolis › archive › dc_ed850d1cb324
AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems — arXiv:2609.12320
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12320
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:39.391Z
- SHA-256 of the archived text
b0da9bf948a062462349d79399f453adfe141d65684abd0dbba5daffbc763e3f- Stable URL of this page
https://metraipolis.com/documento/dc_ed850d1cb324
How to cite
AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems — arXiv:2609.12320 — arXiv (en), https://arxiv.org/abs/2609.12320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed850d1cb324 (Metraipolis archive dc_ed850d1cb324, sha256 b0da9bf948a062462349d79399f453adfe141d65684abd0dbba5daffbc763e3f)
BibTeX
@misc{dced850d1cb324,
title = {AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems — arXiv:2609.12320},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12320},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed850d1cb324; sha256 b0da9bf948a062462349d79399f453adfe141d65684abd0dbba5daffbc763e3f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM systems to persistently manage private and shared memory. AIM dynamically classifies information as private, scoped to one user and inaccessible to others, or public, accessible to all users. It enforces index-level access controls so that private memories are retrievable only by their owner, protecting sensitive data while allowing beneficial shared knowledge to improve coordination and consistency. We also introduce MUMBench (Multi-User Memory Benchmark), a dataset of multi-user interactions containing private and shareable information across four domains. To our knowledge, MUMBench is the first public dataset designed to evaluate multiple memory operations, including retrieval, creation, update, and deletion, in a multi-user environment. Across three independent runs on MUMBench, AIM achieves 96.0% visibility classification accuracy, 58.8% strict operation accuracy, and 70.5% state-aware operation accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.12320 — 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 2026-10-16T02:51:27.774Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).