llms.txt: Does It Actually Work for GEO? (Evidence-Based)

llms.txt does not work for GEO. A 2025 study of 300,000 domains by SERanking found no measurable correlation between llms.txt presence and AI citation rates. Google has explicitly stated it does not support llms.txt. The evidence base is clear: time spent on llms.txt is time not spent on strategies with measured lift.

This guide walks through what llms.txt was supposed to do, what the evidence says, which AI engines (do not) support it, and where to invest instead. If you are deciding whether to add llms.txt to your site, the answer is: only after every higher-impact GEO strategy is in place.

What is llms.txt

llms.txt is a proposed standard for a Markdown-formatted file hosted at /llms.txt on the root of a domain. The intent was to give AI models a curated, machine-readable summary of a site's content — the way robots.txt tells crawlers what they may access, llms.txt would tell models what the site is about.

The proposal gained traction in mid-2024 among SEO practitioners searching for a GEO equivalent of robots.txt. Several major sites published llms.txt files, and tooling emerged to generate them automatically. The hypothesis: AI engines would fetch llms.txt and use it to improve retrieval accuracy.

The SERanking study: 300,000 domains

SERanking ran the largest empirical test of llms.txt effectiveness in 2025. They analyzed 300,000 domains, comparing AI citation rates between sites that published llms.txt and sites that did not, controlling for content quality, domain authority, and topic.

"We found no measurable correlation between llms.txt presence and AI citation rates across the 300,000 domains studied. The signal was indistinguishable from noise."

The finding is consistent with how AI search engines actually work. Models like ChatGPT Search, Perplexity, and Google AI Overviews retrieve and cite from their indexed corpus, not from a site-provided summary file. A self-described summary at /llms.txt would be trivial to manipulate, which is one reason AI engines do not consume it as a citation signal.

Which AI engines support llms.txt

Source: Google Search Central documentation (2025), OpenAI platform docs, Perplexity documentation, Anthropic announcements, SERanking 2025 study.

Why llms.txt fails the GEO test

Three reasons explain why llms.txt does not deliver visibility lift:

1. 1.
   AI engines cite from indexed content, not summaries

   Citation requires verifiable text the re-ranker can attribute. A self-authored summary at /llms.txt is not citable — AI engines would be quoting the site about itself.

2. 2.
   Self-description is trivially gameable

   A site could claim anything in its llms.txt. AI engines cannot trust self-description as a ranking signal. They rely on independent retrieval from indexed content.

3. 3.
   No engine has announced consumption

   Without engine-side support, publishing llms.txt is a one-sided action. Even Anthropic, which published its own llms.txt, has not announced that Claude consumes llms.txt as a retrieval signal.

Where to invest instead

The Princeton GEO study quantified the lift from strategies that actually work. Compare the lifts:

Sources: Aggarwal et al., KDD 2024 (Princeton GEO-bench). SERanking 2025 llms.txt study. Seer Interactive 2025 AIO extraction analysis.

If you still want to publish llms.txt

llms.txt is not harmful — it simply does not help. If you have implemented every higher-impact strategy and have spare time, publishing an llms.txt costs minimal effort. The risk is opportunity cost: time spent on llms.txt is time not spent on strategies with proven lift.

If you publish one, keep it accurate, concise, and aligned with your visible site content. Do not use llms.txt to make claims that do not appear in your indexed content — at best it is ignored, at worst it could be flagged as inconsistent if AI engines ever do consume it.

Frequently asked questions