From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions.
Key points
- 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.
- 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.
- Ablations and a semantic-collapse probe support complementary contributions from epistemic separation, consolidation, and agentic retrieval.
Sources (1)
- [1]From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term DialoguearXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 06:21 AM
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.
Extractive summary: sentences quoted from the sources.