Skip to content
  1. Home
  2. AI tools
  3. AutoGEO

AutoGEO

Research code that learns generative-engine preferences and rewrites content

What it is

Code for an ICLR 2026 paper from CMU. It mines content-preference rules from generative search engines, then rewrites documents to raise their visibility in generated answers while preserving accuracy, either through a prompt-based API model or small released fine-tuned checkpoints. For researchers and technical SEO people testing GEO claims empirically.

Good for

  • Reproduce GEO experiments from the paper
  • Extract engine preference rules for a domain
  • Benchmark a rewriting approach

Install or run

git clone --recursive https://github.com/cxcscmu/AutoGEO

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Conda environment; model API keys in keys.env

Worth knowingResearch code evaluated on benchmarks, not a production tool; results on live AI search products are not guaranteed.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • MarkItDown

    microsoft/markitdown

    Lightweight Python utility that converts files to Markdown for LLMs

    ToolGitHub stars: 195k
  • RAGFlow

    infiniflow/ragflow

    Self-hosted RAG engine with document parsing and agent templates

    ToolGitHub stars: 94k
  • Docling

    docling-project/docling

    Parse PDFs, Office files and more into structured data for LLMs

    ToolGitHub stars: 71k
  • serviette

    pathwaycom/serviette

    No-code RAG server that keeps answers in sync with a document folder

    ToolGitHub stars: 59k