Abstract: Designing biomass-derived activated carbons (ACs) is challenged by heterogeneous synthesis routes and multiobjective trade-offs among specific surface area (SBET), total pore volume (VT), and mass yield (Yield). This study presents a mechanism-enhanced multitask distillation framework (AC-ResKD) built on a shared residual ResDNN and dual priors from prediction-level (PD-KD) and teacher-aware (TA-KD) distillation. Process factors (agent, activation temperature/time, impregnation, heating rate, precursor composition) are modeled jointly with teacher predictions to learn an interpretable mapping across combined and separated one-step/two-step datasets. All results are reported as the mean and 95% confidence intervals over 20 repeated random 80/20 splits. On separated routes, TA-KD achieves robust accuracy for SBET (one-step: R²=0.806 [0.787, 0.824]; two-step: R²=0.801 [0.773, 0.830]) and VT (one-step: R²=0.787 [0.764, 0.810]; two-step: R²=0.817 [0.791, 0.843]). On the combined set, TA-KD yields the strongest gains for Yield (R²=0.816 [0.802, 0.831]; RMSE=5.047 [4.853, 5.242]) while improving SBET and VT as well. Overall, Yield is the most consistent beneficiary of distillation, and route-separated training exhibits improved monotonicity and reduced bias relative to combined training; the two-step route shows stronger VT predictability consistent with a pre-carbonization priming effect. Explainability (PFI/SHAP) identifies teacher outputs, agent type, and thermal severity as dominant drivers. Impregnation governs VT in one-step activation, while pyrolysis variables rise in importance in two-step activation. Robust Pareto screening with quantile-window extraction delivers agent- and route-specific operating envelopes (temperature-dose-time), enabling simultaneous SBET/VT improvement under bounded Yield penalties. AC-ResKD thus provides accurate, interpretable, and actionable guidance for AI-assisted AC design in heterogeneous, data-scarce settings.