Automated Algorithm Discovery

Automated algorithm discovery studies how to construct or improve executable procedures—such as heuristics, numerical solvers, learning rules, and hardware policies—without specifying every design choice by hand. Common approaches use evolutionary or tree search with language models to modify code, program synthesis over reusable components, reinforcement learning, or learned search controllers; candidates are assessed with benchmarks, simulators, formal checks, and staged evaluation. Persistent memory, modular representations, diversity archives, and adaptive budget allocation help reuse findings and reduce search stagnation. A central challenge is establishing that gains reflect sound, useful algorithms rather than benchmark overfitting, noisy evaluations, recombinations of human designs, or exploitable evaluators—and that they transfer under real-world constraints.