AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

MemoryART: Enhancing LLMs via Multi-Memory Models with Adaptive Resonance Theory for Healthcare Agents

Renke Dai, Hebin Hu, Jiahui Zhang, Yilin Kang, Ah-Hwee Tan

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MemoryART instead of MemoryOS for memoryDeepseek-R1 · MediLongChat CDRF1: 52.17 -> 69.61Improved
use MemoryART instead of MemoryOS for memoryGPT-4o mini · MediLongChat CDRF1: 48.76 -> 74.62Improved
add MemoryART episodic memory to the LLM (vs no-memory baseline)GPT-4o mini · MediLongChat IDRF1: 23.30 -> 38.79Improved
add MemoryART memory (vs no-memory baseline)Deepseek-R1 · MediLongChat SRaccuracy: 80.00 -> 85.00Improved
add MemoryOS memory (vs no-memory baseline)Deepseek-R1 · MediLongChat SRaccuracy: 80.00 -> 66.67Hurt
use MemoryART instead of MemoryOSGPT-4o-mini · LoCoMo Single HopF1: 35.27 -> 31.43Hurt
use MemoryART instead of MemoryOSGPT-4o-mini · LoCoMo TemporalF1: 20.02 -> 27.46Improved
use MemoryART instead of MemoryOSDeepseek-R1 · MediLongChattoken count: 13503 -> 6101Improved
increase number of retrieved events k (ablation)MemoryART · MediLongChat IDRF1Mixed
add more similarity channels m (timestamp, symptom, structure) (ablation)MemoryART · MediLongChat IDR and CDRF1 and BLEUImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy