logo
ResearchBunny Logo
MIRIX: Multi-Agent Memory System for LLM-Based Agents

Computer Science

MIRIX: Multi-Agent Memory System for LLM-Based Agents

Y. Wang and X. Chen

Meet MIRIX: a modular, multi-agent memory system that helps language models truly remember by supporting rich visual and multimodal experiences through six structured memory types. On ScreenshotVQA it boosts accuracy by 35% vs RAG while cutting storage 99.9%; on LOCOMO it reaches 85.4%. Research conducted by Yu Wang (MIRIX AI) and Xi Chen (MIRIX AI).... show more
Citation Metrics
Citations
1
Influential Citations
9
Reference Count
34
Citation by Year

Note: The citation metrics presented here have been sourced from Semantic Scholar and OpenAlex.

Related Publications

Explore these studies to deepen your understanding of the subject.

Deep learning-based multi-criteria recommender system for technology-enhanced learning
Computer Science

Deep learning-based multi-criteria recommender system for technology-enhanced learning

L. Salau, H. Mohamed, et al.

Not-for-profit or for-profit? Research on the high-quality development path of private universities in China based on system dynamics
Education

Not-for-profit or for-profit? Research on the high-quality development path of private universities in China based on system dynamics

S. Duan, H. Yang, et al.

A neuromorphic physiological signal processing system based on VO₂ memristor for next-generation human-machine interface
Engineering and Technology

A neuromorphic physiological signal processing system based on VO₂ memristor for next-generation human-machine interface

R. Yuan, P. J. Tiw, et al.

SLEAP: A deep learning system for multi-animal pose tracking
Biology

SLEAP: A deep learning system for multi-animal pose tracking

T. D. Pereira, N. Tabris, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny