We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation.

翻译：我们在每智力瓦特框架下发展了算法催化的热力学理论，识别出可重用计算结构，这些结构能够减少任务类别的不可逆操作，同时满足有界恢复和结构选择性约束。我们证明任何特定类别的加速上限由底层系统与类别描述符之间的算法互信息决定，且编码该信息通过兰道尔擦除需支付最小热力学代价。综合这些结果，我们得到一个耦合定理，该定理给出了算法催化剂在能量上有利所需部署时间的下界。该框架通过仿射SAT类进行说明，并将当代学习系统置于智能计算的信息热力学约束之中。