AI RESEARCH
What Gets Cited: Competitive GEO in AI Answer Engines
arXiv CS.AI
•
ArXi:2605.25517v1 Announce Type: new AI answer engines generate answers from retrieved pages but cite only a few sources. This makes visibility depend not just on ranking, but on being cited. We study competitive Generative Engine Optimization (GEO): when two retrieved candidates compete, what makes one likely to be cited first? We build a controlled two-document retrieval-augmented generation (RAG) testbed that injects exactly two candidate sources into the model context and measures which source is referenced by the first citation marker in the output.