Metraipolis › archive › dc_5bf95e6c975f

Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents — arXiv:2609.32511

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32511
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:36.384Z
SHA-256 of the archived text
7ffcf8b9315cca2ae417974c131ef8e11b1d8b8a7aeaef2a036558c49ce513db
Stable URL of this page
https://metraipolis.com/documento/dc_5bf95e6c975f

How to cite

Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents — arXiv:2609.32511 — arXiv (en), https://arxiv.org/abs/2609.32511 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bf95e6c975f (Metraipolis archive dc_5bf95e6c975f, sha256 7ffcf8b9315cca2ae417974c131ef8e11b1d8b8a7aeaef2a036558c49ce513db)
BibTeX
@misc{dc5bf95e6c975f,
  title = {Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents — arXiv:2609.32511},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32511},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bf95e6c975f; sha256 7ffcf8b9315cca2ae417974c131ef8e11b1d8b8a7aeaef2a036558c49ce513db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32511. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents serving different users often solve related tasks, yet separate user histories can leave reusable experience inaccessible to other agents. Pooling memories expands access but risks transferring preferences that conflict with the receiving user's requirements. We introduce ShareMem, a memory architecture that shares reusable experience while grounding its application in the receiving user's own preferences. Shared experiences indicate how to act and which preferences to consult; the receiving user's memory supplies their concrete values. Two-stage consolidation refines experience locally before integrating accepted edits into a shared pool. During execution, scope-first retrieval jointly selects local and shared experiences under a common entry budget, while a user-bound channel supports initial and agent-initiated preference retrieval. We evaluate ShareMem across web navigation (Mind2Web), online personalized interaction (VitaBench~2.0), and multi-session coding (MemoryCode) with four backbone models. It improves step success, average task success, and dialogue-macro coding scores, respectively, over matched user-local memory across all four models. Ablations favor two-stage consolidation for smaller shared pools, lower induction token usage, and better downstream performance, and support complementarity between experience guidance and active preference retrieval. Further analyses show that sharing helps most when relevant local experience is scarce, while source quality and cross-user preference interference limit useful transfer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32511 — 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 2026-10-07T20:29:00.838Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).