Metraipolis › archive › dc_b27913c57764

Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents — arXiv:2610.02002

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02002
License (as archived)
CC0-1.0
Archived
2026-10-06T12:15:41.393Z
SHA-256 of the archived text
83c538290b21f6f7098875362f00a6ec16cc2b962a542f4563a6fc454add4d1c
Stable URL of this page
https://metraipolis.com/documento/dc_b27913c57764

How to cite

Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents — arXiv:2610.02002 — arXiv (en), https://arxiv.org/abs/2610.02002 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b27913c57764 (Metraipolis archive dc_b27913c57764, sha256 83c538290b21f6f7098875362f00a6ec16cc2b962a542f4563a6fc454add4d1c)
BibTeX
@misc{dcb27913c57764,
  title = {Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents — arXiv:2610.02002},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02002},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b27913c57764; sha256 83c538290b21f6f7098875362f00a6ec16cc2b962a542f4563a6fc454add4d1c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02002. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02002 — 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 2026-10-06T10:21:28.233Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).