Research
Watts-per-Intelligence Part II: Algorithmic Catalysis
arXiv:2604.20897v1 Announce Type: cross Abstract: We develop a thermodynamic theory of algorithmic catalysis within the watts-per-intelligence framework, identifying reusable computational structures
arXiv:2604.20897v1 Announce Type: cross Abstract: 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 installing 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 a catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within a unified information-thermodynamic constraint on intelligent computation.
Related
- QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
- GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
- Resource Consumption Threats in Large Language Models
Source: arXiv cs.AI | 2026-04-24