Context
This paper introduces Computational Language Processing (CLP), a novel framework for discovering algorithms through the automation of algorithmic discovery. By treating algorithms as sequences of operations represented as tokens, CLP enables the chaining of these tokens using a grammar to form complex procedures. This approach allows for the exploration and generation of new algorithms that can outperform existing methods in solving NP-hard combinatorial optimization problems and foundational quantum computing tasks.
Abstract
Algorithms are the engine for reproducible problem-solving. We present a framework automating algorithm discovery by conceptualizing them as sequences of operations, represented as tokens. These computational tokens are chained using a grammar, enabling the formation of increasingly sophisticated procedures. Our ensemble Monte Carlo tree search (MCTS) guided by reinforcement learning (RL) explores token chaining and drives the creation of new tokens. This methodology rediscovers, improves, and generates new algorithms that substantially outperform existing methods for strongly NP-hard combinatorial optimization problems and foundational quantum computing approaches such as Grover’s and Quantum Approximate Optimization Algorithm. Operating at the computational rather than code-generation level, our framework produces algorithms that can be tailored specifically to problem instances, not merely classes.