Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can inspect datasets, generate code, and produce analyses end-to-end. However, we show that they frequently make subtle inferential errors that lead to incorrect conclusions despite correctly executed analyses. Existing benchmarks fail to capture this failure mode, as they rarely assess whether a reported p-value is statistically valid given the assumptions underlying the data. We address this gap by building P-Bench, a benchmark comprising 425 open-ended, realistic hypothesis-testing tasks spanning economics, biology,...
| Authors | Jiacheng Miao, Jin Mu, Guanhua Chen et al. |
|---|---|
| Primary category | cs.AI |
| Published | 7 August 2026 |
| Last updated at source | 7 August 2026 |
Connected in the knowledge graph
- May2222/P-BenchDataset · cited by
Models and datasets referencing this paper
- May2222/P-BenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.