Metraipolis › archive › dc_98caed187d9a

Lifelong Context Adaptation through Bidirectional Memory-Skill Learning — arXiv:2610.32295

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32295
License (as archived)
CC0-1.0
Archived
2026-10-26T19:50:32.986Z
SHA-256 of the archived text
8afff3869398682d71ca9a30ca3f36adf5ae8771b29c7196dadfc394bb46b6af
Stable URL of this page
https://metraipolis.com/documento/dc_98caed187d9a

How to cite

Lifelong Context Adaptation through Bidirectional Memory-Skill Learning — arXiv:2610.32295 — arXiv (en), https://arxiv.org/abs/2610.32295 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98caed187d9a (Metraipolis archive dc_98caed187d9a, sha256 8afff3869398682d71ca9a30ca3f36adf5ae8771b29c7196dadfc394bb46b6af)
BibTeX
@misc{dc98caed187d9a,
  title = {Lifelong Context Adaptation through Bidirectional Memory-Skill Learning — arXiv:2610.32295},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32295},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98caed187d9a; sha256 8afff3869398682d71ca9a30ca3f36adf5ae8771b29c7196dadfc394bb46b6af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32295. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Lifelong LLM agents must learn from an expanding history of interactions while making each decision within a bounded context window. Memory makes past experience available, but the agent may still need to infer how to solve each new task from the retrieved records. Skills provide reusable procedures, yet may omit the task-specific facts needed to apply them. Because retrieved memory and skills shape the agent's behavior, they also influence the experience available for future learning. We introduce MemCryst, a framework for lifelong context adaptation through bidirectional learning of memory and skills with a frozen language model. Recurring episodes stored in memory support skill creation and revision, and the interactions guided by those skills supply new memory for subsequent learning. Facts retrieved from memory and learned skills jointly form the agent's context, while task outcomes adjust the future retrieval influence of the records actually served without rewriting their content. Across ten settings spanning embodied control, long-document reading, conversation, mathematics, and code, MemCryst leads seven reported comparisons. On ALFWorld, joint serving achieves 63.17% success, compared with 59.83% for memory-only and 50.50% for skill-only serving. Code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.32295 — 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 2026-10-26T19:45:33.304Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).