Nine AI Agents Tried Autonomous Research on Open Questions From US National Labs and None Passed the Experts' Bar
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.5 Articles
5 Articles
114 Of 135 AI Agent Papers Failed The Integrity Check » Saipien
The test was not whether an AI agent could sound like a scientist. It was whether the agent would do the science, then write it up so the paper matched the run. Into the Unknown, by Seungone Kim and colleagues, is a benchmark of 15 open research problems. Each one is a follow-up direction a […]
Nine AI agents completed 135 open-ended research attempts linked to national U.S. laboratories, but no delivery met both integrity, completeness and expert quality criteria.
The Into the Unknown benchmark, developed under the auspices of Carnegie Mellon, tested AI agents with unsolved research questions. None of the 135 studies of nine agents met the specialist conditions.
Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar
The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments that never took place. GPT-6 Astra performs best but still doesn't meet the experts' standards. The article Nine AI agents tried autonomous research on open questions from U…
The benchmark "Into the Unknown" allows nine AI agents to work on open research questions from US national laboratories. None of the 135 submissions meets all requirements. 114 work is already going through during the integrity check: the agents claim experiments that never took place. GPT-6 Astra is still doing the best, but does not reach the bar of experts either. The article Benchmark lets AI agents work on open research questions – not a si…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
