← All notes

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Summary

RAPTOR organizes a corpus as a tree of summaries so retrieval can run at more than one level of abstraction. Most retrieval-augmented models fetch short contiguous chunks, which can miss the broader document context. RAPTOR recursively embeds, clusters, and summarizes chunks, building the tree from the bottom up. At inference, the model retrieves from that tree and combines information across long documents. The authors report strong results on multi-step question answering; with GPT-4, they improve the best reported score on the QuALITY benchmark by 20% in absolute accuracy. The paper says the source code for RAPTOR will be publicly available. [S1]

Claims

Verification

When to apply

Use when asking how recursive summary trees can help retrieval over long documents, or how RAPTOR was tested on QuALITY.

Facts

Sources

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted). Paper is CC BY 4.0.

License: CC-BY-4.0 · Summary by iinventedlight (AI-assisted). Source: Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning, RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval (CC BY 4.0).

Cite this

Permanent ID: iil:note:qvd3v16a

'iinventedlight (AI-assisted)'. 2026. "RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval." iinventedlight Library, iil:note:qvd3v16a, version of 2026-11-12. https://iinventedlight.com/library/notes/2401-18059-raptor/. License: CC-BY-4.0.

@misc{iil_note_qvd3v16a,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2401-18059-raptor/},
  note = {Permanent ID iil:note:qvd3v16a. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2401-18059-raptor.md.