Temporal and spatial stability of the vegetation–climate relationship is a basic ecological assumption for pollen-based quantitative inferences of past climate change and for predicting future vegetation. We explore this assumption for the Holocene in eastern continental Asia (China, Mongolia). Boosted regression trees (BRT) between fossil pollen taxa percentages (Abies, Artemisia, Betula, Chenopodiaceae, Cyperaceae, Ephedra, Picea, Pinus, Poaceae and Quercus) and climate model outputs of mean annual precipitation (Pann) and mean temperature of the warmest month (Mtwa) for 9 and 6 ka (ka = thousand years before present) were set up and results compared to those obtained from relating modern pollen to modern climate. Overall, our results reveal only slight temporal differences in the pollen–climate relationships. Our analyses suggest that the importance of Pann compared with Mtwa for taxa distribution is higher today than it was at 6 ka and 9 ka. In particular, the relevance of Pann for Picea and Pinus increases and has become the main determinant. This change in the climate–tree pollen relationship parallels a widespread tree pollen decrease in north-central China and the eastern Tibetan Plateau. We assume that this is at least partly related to vegetation–climate disequilibrium originating from human impact. Increased atmospheric CO2 concentration may have permitted the expansion of moisture-loving herb taxa (Cyperaceae and Poaceae) during the late Holocene into arid/semi-arid areas. We furthermore find that the pollen–climate relationship between north-central China and the eastern Tibetan Plateau is generally similar, but that regional differences are larger than temporal differences. In summary, vegetation–climate relationships in China are generally stable in space and time, and pollen-based climate reconstructions can be applied to the Holocene. Regional differences imply the calibration-set should be restricted spatially.