Metraipolis › archive › dc_8713ccbdd369

MemFit: Efficient Long-Term Agentic Memory — arXiv:2610.00872

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00872
License (as archived)
CC0-1.0
Archived
2026-10-06T12:02:59.970Z
SHA-256 of the archived text
6c882f11cfff090823ce88f41fa6fee04c1af8072ada0fe6069e09e0c09aa7b6
Stable URL of this page
https://metraipolis.com/documento/dc_8713ccbdd369

How to cite

MemFit: Efficient Long-Term Agentic Memory — arXiv:2610.00872 — arXiv (en), https://arxiv.org/abs/2610.00872 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8713ccbdd369 (Metraipolis archive dc_8713ccbdd369, sha256 6c882f11cfff090823ce88f41fa6fee04c1af8072ada0fe6069e09e0c09aa7b6)
BibTeX
@misc{dc8713ccbdd369,
  title = {MemFit: Efficient Long-Term Agentic Memory — arXiv:2610.00872},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00872},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8713ccbdd369; sha256 6c882f11cfff090823ce88f41fa6fee04c1af8072ada0fe6069e09e0c09aa7b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00872. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in costly, inefficient write operations. To address this limitation, we propose MemFit, a long-term memory system for conversational agents that reduces the cost and latency of memory operations. Unlike existing systems that rely on expensive LLM calls for memory construction or discard surface-level details through compression, MemFit stores each turn verbatim in an append-only store with near-instantaneous, LLM-free insertion, indexing turns with segment summaries rather than replacing them. Additionally, MemFit uses an LLM-free, multi-path retrieval strategy that combines lexical and semantic signals with cross-encoder reranking over caption- augmented episodes in both textual and multimodal settings. Empirical results on three widely used benchmarks, LoCoMo, MemGallery, and LongMemEval-S, show that MemFit achieves state-of-the-art performance while reducing memory construction time and cost several-fold, providing a scalable and efficient solution for persistent agentic memory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00872 — 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 2026-10-06T10:21:27.892Z 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).