Metraipolis › archive › dc_b5f5504046ac

Long-Term Agent Memory through Complementary Curation and Consolidation — arXiv:2610.39790

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39790
License (as archived)
CC0-1.0
Archived
2026-10-31T06:06:50.370Z
SHA-256 of the archived text
bd98c18408c88961d6e6a1138fcd715011b6fdec192efcc064292781c7ee69bd
Stable URL of this page
https://metraipolis.com/documento/dc_b5f5504046ac

How to cite

Long-Term Agent Memory through Complementary Curation and Consolidation — arXiv:2610.39790 — arXiv (en), https://arxiv.org/abs/2610.39790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5f5504046ac (Metraipolis archive dc_b5f5504046ac, sha256 bd98c18408c88961d6e6a1138fcd715011b6fdec192efcc064292781c7ee69bd)
BibTeX
@misc{dcb5f5504046ac,
  title = {Long-Term Agent Memory through Complementary Curation and Consolidation — arXiv:2610.39790},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39790},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5f5504046ac; sha256 bd98c18408c88961d6e6a1138fcd715011b6fdec192efcc064292781c7ee69bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.39790 — 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 2026-10-31T06:06:38.432Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).