From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue

# From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Source: [https://arxiv.org/abs/2610.11314](https://arxiv.org/abs/2610.11314)
[View PDF](https://arxiv.org/pdf/2610.11314)[HTML \(experimental\)](https://arxiv.org/html/2610.11314v1)

> Abstract: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](https://github.com/Silent-Rain02/CogMem)\.

## Submission history

From: ZiRui Liao \[[view email](https://arxiv.org/show-email/359934e9/2610.11314)\] **\[v1\]**Thu, 8 Oct 2026 06:21:45 UTC \(1,417 KB\)