This work from our lab tackles (IMO) one of the most important (and impactful) new problems in our agentic world: clickbait for agents. It was fun presenting this at EMNLP (even if it was rejected from @arxiv)!
Now that we've been asking GPT, Claude and Gemini and let them search for us, what make them click, read, and present?
It turns out they are highly susceptible, and we are able to learn a simple content presentation strategy that makes 𝐆𝐏𝐓-𝟓-𝐦𝐢𝐧𝐢 𝐜𝐥𝐢𝐜𝐤 𝟗𝟖.𝟓% 𝐨𝐟
