One 8B model stops using a fixed reasoning template: AlgoPilot picks a paradigm and writes the formulation, lifting average accuracy from 38.4% to 72.9%
AlgoPilot splits language-model problem solving into three steps: decide whether a problem calls for natural-language reasoning, code execution, constraint solving, symbolic planning or mathematical optimization; generate a structured formulation for the chosen paradigm; then let an execution model solve it. With Qwen3-8B as the executor, average accuracy on 13 benchmarks spanning 66 domains rises from 38.4% under direct prompting to 72.9%, 11.7 points above the best large-model prompting baseline GLM-5; with Gemma-4-E4B-it as the executor, average success rises from 39.0% under direct prompting to 60.5%.