Metraipolis › archive › dc_f62e620fe2a7
EvoMemState: Evolving Memory State for Personal Agents — arXiv:2611.03743
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03743
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:35:38.465Z
- SHA-256 of the archived text
c147a4befdf87168816bbd947d0d4d7e06432f2bf2b2346148150e9942bd408a- Stable URL of this page
https://metraipolis.com/documento/dc_f62e620fe2a7
How to cite
EvoMemState: Evolving Memory State for Personal Agents — arXiv:2611.03743 — arXiv (en), https://arxiv.org/abs/2611.03743 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f62e620fe2a7 (Metraipolis archive dc_f62e620fe2a7, sha256 c147a4befdf87168816bbd947d0d4d7e06432f2bf2b2346148150e9942bd408a)
BibTeX
@misc{dcf62e620fe2a7,
title = {EvoMemState: Evolving Memory State for Personal Agents — arXiv:2611.03743},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03743},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f62e620fe2a7; sha256 c147a4befdf87168816bbd947d0d4d7e06432f2bf2b2346148150e9942bd408a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03743. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independent facts. This fact-centric paradigm may overlook how new facts update, constrain, or conflict with earlier ones, while leaving their applicability, role, and priority for the current request implicit. In this paper, we introduce EvoMemState, a state-centric framework that augments persistent facts with two complementary states: Relational States that capture how facts remain valid and relate to one another as memory evolves, and a Reasoning State that determines how these facts should be applied to the current request. Specifically, EvoMemState consists of three key components: (i) Ontology-Guided Memory State Induction extracts Persistent Facts and constructs Relational States that maintain their validity, scope, and evolving relations. (ii) RL-Based State Evolution internalizes memory-use experience into a policy through reinforcement learning to generate a request-specific Reasoning State. (iii) State-Aware Reasoning then combines the relevant facts with their Relational States and the generated Reasoning State to guide the personal agent. Extensive experiments on long-term dialogue and memory-use benchmarks demonstrate consistent improvements over existing memory systems in retrieval completeness and memory-grounded response accuracy. Our code and implementation details are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.03743 — 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 2026-11-04T18:32:37.380Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).