---
title: 'HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'This note is CC BY 4.0. It links to the paper and does not reproduce it. Paper license: arXiv non-exclusive distribution (verified on arXiv abs page 2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/).'
source: https://iinventedlight.com/library/notes/2405-14831-hipporag.md
source_license: 'arXiv default (non-exclusive distribution license)'
attribution: 'Pointer note by iinventedlight (AI-assisted). Links to: Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su, HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (arXiv). This note does not reproduce the paper.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Pointer note only. Abs page read 2026-11-11. The paper is not reproduced here.'
category: arxiv
topic_area: 'ai-research: memory-and-context'
tags: arxiv, pointer, memory-and-context, RAG
arxiv_id: 2405.14831
alias: 2405.14831-hipporag
format: pointer
type: pointer
sources:
  - id: S1
    title: 'HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models'
    publisher: arXiv
    authors: 'Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su'
    url: https://arxiv.org/abs/2405.14831
    version_read: 'v3 (14 Jan 2025)'
    accessed: 2026-11-11
    license: 'arXiv default (non-exclusive distribution license)'
---
# HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

## Summary
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (2024), by Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su, is at https://arxiv.org/abs/2405.14831. The authors present HippoRAG as a retrieval framework meant to integrate new experiences after pre-training more effectively than ordinary RAG. They combine language models, knowledge graphs, and Personalized PageRank in a way they compare to roles of the neocortex and hippocampus. On multi-hop question answering they report gains of up to 20% over prior RAG methods. They also report that a single HippoRAG retrieval step can match or beat iterative retrieval such as IRCoT while being 10-30 times cheaper and 6-13 times faster, with further gains when the two are combined. Code and data are pointed to https://github.com/OSU-NLP-Group/HippoRAG. Code and data are available at https://github.com/OSU-NLP-Group/HippoRAG. Title, authors, abstract, and comments were taken from the arXiv abs page. The version is v3 (14 Jan 2025), submitted 23 May 2024.

## Claims
Pointer notes do not quote the paper. See Verification and Sources for the link and license.

## Verification
- Format: pointer note only. The paper is not reproduced here.
- Why it matters: It matters as a distinctive alternative to flat retrieval: a hippocampal-inspired knowledge graph used as long-term associative memory.
- Reproduced: not reproduced (2026-11-11).
- Related work: Related notes already in the library include [MemGPT](https://iinventedlight.com/library/notes/2310-08560-memgpt/) and [Self-RAG](https://iinventedlight.com/library/notes/2310-11511-self-rag/).
- Limits: This is a pointer note only. The 20% gain and the 10-30x / 6-13x cost and speed comparisons are the authors' reported results from the v3 paper (14 Jan 2025).
- License: arXiv default (non-exclusive distribution license) on the abs page (2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/). Submitted 23 May 2024 (v1); last revised 14 Jan 2025 (v3). Sources: [S1] https://arxiv.org/abs/2405.14831, v3 (14 Jan 2025). checked_on: 2026-11-11. Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it. The note itself is CC BY 4.0.

## When to apply
Use when looking at graph-based or associative alternatives to flat retrieval for long-term model memory.

## Facts
- id: F1
  claim: 'HippoRAG is a retrieval framework inspired by hippocampal indexing theory, combining language models, knowledge graphs, and Personalized PageRank.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F2
  claim: 'The authors report that it outperforms state-of-the-art RAG methods on multi-hop question answering by up to 20%.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F3
  claim: 'They report that single-step retrieval with HippoRAG is comparable or better than iterative retrieval like IRCoT while being 10-30 times cheaper and 6-13 times faster, and they point to https://github.com/OSU-NLP-Group/HippoRAG.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0

## Sources
- [S1] arXiv 2405.14831, https://arxiv.org/abs/2405.14831. Paper license: arXiv default (non-exclusive distribution license). v3 (14 Jan 2025). Accessed 2026-11-11. This note links to the paper and does not reproduce it.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).