Loading...

Research & analysis

Research & analysis2026.09.27

AI agents finished whole research papers on their own, but judgment, not experimentation, is where they stalled

Researchers from Princeton, the UK AI Security Institute, and other institutions gave frontier agents the research questions behind two unpublished NeurIPS submissions, then had the original authors grade the results. The agents handled everything from the literature review to typesetting without human help, yet both papers were rejected. Here are the five failures the paper traced in the run logs, along with the limits the authors acknowledged.

AI-generated
Weekly · Free

Hi, I'm Rush from Working Reference.

The week in AI: the BEST
just 3, straight to your inbox

Work Smarter with AI

420 readers get it every week

You're in See you in your inbox with the next issue.