The Natural Resources Conservation Service -Curve Number (NRCS-CN) model was originally developed to simulate runoff from a given storm on small agricultural watersheds having mild terrain slope (< 5%), but it has been applied in diverse field conditions and even much beyond its intended scope. The use of published CN table without slope adjustment and with a fixed initial abstraction ratio (lambda = 0.2) has resulted in severe underesti-mation of runoff. In this study, the effect of slope on CN and lambda was investigated using the measured rainfall-runoff data from small experimental plots in India. The investigation corroborated the requirement of a slope-adjusted CN equation suited for Indian hydro-climatic conditions, so three slope-adjusted CN models (CN2 theta) having lambda decaying with slope (theta) were proposed to improve the surface runoff prediction. The proposed models were calibrated and validated using 390 and 127 rainfall-runoff events, respectively, from 39 plots having different land-uses and slopes varying from 5% to 16%. The performance of new models was evaluated using Nash -Sutcliffe Efficiency (NSE), Coefficient of Determination (R2), Normalized Root Mean Square Error (nRMSE), Mean Bias Error (mBIAS), and 1:1 plot. The proposed models exhibited superior performance statistics to existing CN adjustment models for both lambda = 0.2 and 0.03. Also, the use of proposed CN2 theta significantly improved the values of NSE, R-2, nRMSE, mBIAS and regression slope from-0.37, 0.33, 0.960, 10.72 mm and 0.335 to 0.53, 0.61, 0.562,-0.40 mm and 0.865, respectively, as compared to handbook CN values without any slope adjustment.