Metraipolis › archive › dc_0ba492d2b596

Memorilla: Latent Semantic Memory for LLMs — arXiv:2610.21375

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21375
License (as archived)
CC0-1.0
Archived
2026-10-16T09:19:24.442Z
SHA-256 of the archived text
f082a40ed524533213e8bf8e2021040f2ac47d0bbe478c515a34910591d86a2f
Stable URL of this page
https://metraipolis.com/documento/dc_0ba492d2b596

How to cite

Memorilla: Latent Semantic Memory for LLMs — arXiv:2610.21375 — arXiv (en), https://arxiv.org/abs/2610.21375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ba492d2b596 (Metraipolis archive dc_0ba492d2b596, sha256 f082a40ed524533213e8bf8e2021040f2ac47d0bbe478c515a34910591d86a2f)
BibTeX
@misc{dc0ba492d2b596,
  title = {Memorilla: Latent Semantic Memory for LLMs — arXiv:2610.21375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ba492d2b596; sha256 f082a40ed524533213e8bf8e2021040f2ac47d0bbe478c515a34910591d86a2f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier actions. For a frozen LLM, access to this accumulated knowledge is limited to what a memory system places in its context window. However, gathering and combining relevant information needed for each query while keeping the model's context short remains challenging for existing systems. Here we introduce Memorilla, a memory system that gathers information from an entire document collection into a fixed number of query-dependent 'memory tokens' for a frozen LLM. Memorilla encodes documents (such as user chats, book chapters) once into reusable embeddings, then learns to retrieve and place query-specific information in the LLM's input embedding space. Using only 16 memory tokens, Memorilla achieves the best performance against baselines including Mem0 and MemoRAG on five of eight benchmarks spanning personalization, long-document and knowledge-intensive question answering. Notably, on FactKG, it reaches 84.33% accuracy versus 80.43% with full-context inference, while using 108x fewer tokens to represent the source documents. Furthermore, Memorilla can facilitate continual learning in agentic systems where the document count (the agent's past turns) increases throughout the trajectory. In a TextWorld environment, we show that Memorilla reduces the agent's tendency to wander between rooms it has already explored, and improves its average success rate from 18.6% with full-history in-context learning to 24.2%. Overall, Memorilla aids frozen LLMs in accumulating and using knowledge effectively across long-context interactions and takes a step towards building continually learning AI systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.21375 — 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 2026-10-16T08:44:17.939Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).