There’s growing excitement in the AI industry about the idea that today’s leading models could build the next generation of the technology. But a new study recently found top AI agents struggle on the kind of genuinely open-ended research problems required to push the field forward.
Large language models have made rapid progress in many of the day-to-day jobs involved in machine learning research, such as writing code, generating and curating data, and running experiments. Last year, startup Sakana AI’s AI Scientist-v2 even managed to write a paper that cleared peer review for the prestigious International Conference on Learning Representations.
These advances have led to speculation that models are close to being able to build better versions of themselves with little human oversight—a process called recursive self-improvement. The idea underpins predictions that we may be on the verge of an intelligence explosion that could quickly lead to AI superintelligence.
In a recent paper, researchers put the idea to the test using a new approach they call shadow evaluations. This involves taking the research question from a high-quality, unpublished machine learning paper and asking AI agents to solve the problem. The original paper’s authors then grade the results. When the team tested Claude Opus 4.8 on two papers submitted to the prestigious machine-learning conference NeurIPS 2026, the authors rejected both.
“The papers were nowhere close to the mark when it came to being at the quality of a top AI conference,” Sayash Kapoor from Princton University, who co-led the study, told MIT Technology Review.
Previous efforts to get AI agents to do machine learning research have often targeted problems focused on engineering, such as reproducing previous research or training smaller models against a benchmark.
In the new experiments, the researchers challenged models with more open-ended tasks that required them to devise hypotheses, decide what evidence is needed to validate them, judge when a research direction was fruitless, and go back to the drawing board.
One research question was whether the personality traits a language model displays can be measured and adjusted by observing and editing its weights; the other attempted to detect when a model that works with tabular data has quietly stopped being reliable.
In each case, the AI researchers were given $3,000 of API credits, a budget for time on GPUs to run machine learning experiments, a dedicated Linux virtual machine, and unrestricted internet access. They were then given six days to produce a paper that could pass NeurIPS’ stringent peer-review criteria.
In both cases, the models got a good start. The agents surveyed the literature effectively, came up with opening hypotheses that mirrored those of the authors, and successfully ran hundreds of experiments.
But they quickly went off the rails. Although they could monitor their own use of time and their API and GPU budgets, they rushed through the process. One left 110 hours of unused time on the clock, and both failed to spend even 50 percent of their API budget.
Both agents also settled on a research direction within just 10 hours and failed to change approaches despite repeated negative feedback from another AI designed to review drafts of their papers. The reviewer identified problems the human authors would also flag in the final paper, but the models simply added caveats to their findings and ploughed on. Ultimately the papers received a “strong reject” and a “reject” decision from the human reviewers based on NeurIPS grading protocol.
The authors admit their approach has limitations. The reviewers knew AI had written the submissions, and some of the team are on record as doubting an imminent intelligence explosion. The original human-authored papers also took far longer than six days to produce and used many more GPU hours to reach their conclusions (though, as the researchers note, the models did not use their allocated budget in any case).
Nonetheless, the results suggest that today’s models still have some way to go before they can tackle the most challenging problems in machine learning research. Until that happens, the dream of recursive self-improvement is likely to remain a distant prospect.
