Metraipolis › archive › dc_45cc9ef4fa7a

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents — arXiv:2609.23986

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23986
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:41.104Z
SHA-256 of the archived text
a61b5d8aef807e621f555db42260792f2279f2e11bd82b1b9750061e2ecc3a96
Stable URL of this page
https://metraipolis.com/documento/dc_45cc9ef4fa7a

How to cite

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents — arXiv:2609.23986 — arXiv (en), https://arxiv.org/abs/2609.23986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45cc9ef4fa7a (Metraipolis archive dc_45cc9ef4fa7a, sha256 a61b5d8aef807e621f555db42260792f2279f2e11bd82b1b9750061e2ecc3a96)
BibTeX
@misc{dc45cc9ef4fa7a,
  title = {Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents — arXiv:2609.23986},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23986},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45cc9ef4fa7a; sha256 a61b5d8aef807e621f555db42260792f2279f2e11bd82b1b9750061e2ecc3a96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23986 — 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 2026-10-09T06:58:09.619Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).