Preprint · 2025 · Open access

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

Yu Wang, Xi Chen

arXiv (Cornell University) · Published 10 July 2025 · DOI 10.48550/arxiv.2507.07957

Open PDFView at the publisherCite this paper

In brief

“MIRIX: Multi-Agent Memory System for LLM-Based Agents” is a 2025 preprint by Yu Wang and Xi Chen, published in arXiv (Cornell University). OpenAlex counts 243 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
243
Most cited in
2026 (222)
References
29
Authors
2

Abstract

Although memory capabilities of AI agents are gaining increasing attention, existing solutions remain fundamentally limited. Most rely on flat, narrowly scoped memory components, constraining their ability to personalize, abstract, and reliably recall user-specific information over time. To this end, we introduce MIRIX, a modular, multi-agent memory system that redefines the future of AI memory by solving the field's most critical challenge: enabling language models to truly remember. Unlike prior approaches, MIRIX transcends text to embrace rich visual and multimodal experiences, making memory genuinely useful in real-world scenarios. MIRIX consists of six distinct, carefully structured memory types: Core, Episodic, Semantic, Procedural, Resource Memory, and Knowledge Vault, coupled with a multi-agent framework that dynamically controls and coordinates updates and retrieval. This design enables agents to persist, reason over, and accurately retrieve diverse, long-term user data at scale. We validate MIRIX in two demanding settings. First, on ScreenshotVQA, a challenging multimodal benchmark comprising nearly 20,000 high-resolution computer screenshots per sequence, requiring deep contextual understanding and where no existing memory systems can be applied, MIRIX achieves 35% higher accuracy than the RAG baseline while reducing storage requirements by 99.9%. Second, on LOCOMO, a long-form conversation benchmark with single-modal textual input, MIRIX attains state-of-the-art performance of 85.4%, far surpassing existing baselines. These results show that MIRIX sets a new performance standard for memory-augmented LLM agents. To allow users to experience our memory system, we provide a packaged application powered by MIRIX. It monitors the screen in real time, builds a personalized memory base, and offers intuitive visualization and secure local storage to ensure privacy.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, Y., & Chen, X. (2025). MIRIX: Multi-Agent Memory System for LLM-Based Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2507.07957

MLA 9

Wang, Yu, and Xi Chen. “MIRIX: Multi-Agent Memory System for LLM-Based Agents.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2507.07957.

Chicago

Wang, Yu and Xi Chen. 2025. “MIRIX: Multi-Agent Memory System for LLM-Based Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2507.07957.

Harvard

Wang, Y. and Chen, X. (2025) ‘MIRIX: Multi-Agent Memory System for LLM-Based Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2507.07957.

IEEE

Y. Wang and X. Chen, “MIRIX: Multi-Agent Memory System for LLM-Based Agents,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2507.07957.

BibTeX

@misc{wang2025mirix,
  title     = {{MIRIX: Multi-Agent Memory System for LLM-Based Agents}},
  author    = {Wang, Yu and Chen, Xi},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2507.07957},
  url       = {https://doi.org/10.48550/arxiv.2507.07957}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications

  • LLM agents
  • episodic memory
  • semantic memory
  • procedural memory
  • multimodal memory

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wang, Y., & Chen, X. (2025). MIRIX: Multi-Agent Memory System for LLM-Based Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2507.07957

How many times has this paper been cited?

243 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yu Wang, Xi Chen.

What is the DOI of this paper?

10.48550/arxiv.2507.07957, permanently at https://doi.org/10.48550/arxiv.2507.07957. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.