TeLLAgent: a dual-agent framework for reliable scientific discovery with tool-enhanced LLMs.

To evaluate the statistical significance of improvements, as shown in Table S7, a Friedman test was used and revealed highly significant overall differences among the models ( p < 0.001), followed by pairwise Wilcoxon signed-rank tests with Benjamini–Hochberg correction for multiple comparisons.

also in 132,142 other papers