Metraipolis › archive › dc_45ef6ce434af
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue — arXiv:2610.11314
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11314
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:04:13.447Z
- SHA-256 of the archived text
27d725ad4fe8e35bc336f5d990686ca88b6a62a052189c56895a911388977474- Stable URL of this page
https://metraipolis.com/documento/dc_45ef6ce434af
How to cite
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue — arXiv:2610.11314 — arXiv (en), https://arxiv.org/abs/2610.11314 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45ef6ce434af (Metraipolis archive dc_45ef6ce434af, sha256 27d725ad4fe8e35bc336f5d990686ca88b6a62a052189c56895a911388977474)
BibTeX
@misc{dc45ef6ce434af,
title = {From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue — arXiv:2610.11314},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11314},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45ef6ce434af; sha256 27d725ad4fe8e35bc336f5d990686ca88b6a62a052189c56895a911388977474},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11314. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions. However, existing Retrieval-Augmented Generation (RAG) frameworks typically treat memory as passive storage, making it difficult to distinguish source-attributed beliefs from unattributed event/fact records and to connect evidence dispersed across sessions. We introduce CogMem, a cognitive memory architecture based on the PEC$^2$F (Person-Event-Concept-Claim-Fact) graph schema. Dedicated Claim nodes preserve the source and target of subjective statements, while Fact and Event nodes represent semantic and episodic knowledge. Dialogue turns are incrementally converted into provenance-aware graph records, consolidated into higher-level facts, and reconciled into temporally scoped Claim views when the same source provides conflicting updates. For retrieval, a rule-based controller driven by LLM intent parsing composes four deterministic graph operators---anchoring, traversal, intersection, and evidence grounding---to reconstruct query-relevant context. Experiments on LoCoMo and LongMemEval show strong performance, especially on multi-hop, temporal, and knowledge-update tasks. Ablations and a semantic-collapse probe support complementary contributions from epistemic separation, consolidation, and agentic retrieval. Code: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.11314 — 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 2026-10-09T05:47:15.190Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).