Sound Agentic Science Requires Adversarial Experiments
For the scientific community using AI agents in research, it highlights a critical failure mode and proposes a corrective evaluation standard.
The paper argues that LLM-based agents for scientific data analysis risk producing plausible but non-falsifiable claims, and proposes a falsification-first standard where agents actively search for ways claims can fail rather than crafting compelling narratives.
LLM-based agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise. This capability is often framed as an acceleration of discovery, but it also accelerates a familiar failure mode, the rapid production of plausible, endlessly revisable analyses that are easy to generate, effectively turning hypothesis space into candidate claims supported by selectively chosen analyses, optimized for publishable positives. Unlike software, scientific knowledge is not validated by the iterative accumulation of code and post hoc statistical support. A fluent explanation or a significant result on a single dataset is not verification. Because the missing evidence is a negative space, experiments and analyses that would have falsified the claim were never run or never published. We therefore propose that non-experimental claims produced with agentic assistance be evaluated under a falsification-first standard: agents should not be used primarily to craft the most compelling narrative, but to actively search for the ways in which the claim can fail.