Sound Agentic Science Requires Adversarial Experiments

Computer Science > Artificial Intelligence [Submitted on 23 Apr 2026] Sound Agentic Science Requires Adversarial Experiments Dionizije Fa, Marko Culjak 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. Comments: Published at ICLR 2026 Workshop on Agents in the Wild Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.22080 [cs.AI]   (or arXiv:2604.22080v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.22080 Focus to learn more Submission history From: Dionizije Fa [view email] [v1] Thu, 23 Apr 2026 21:24:26 UTC (95 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)