Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Models (LLMs). However, most existing methods adopt a rigid Planning-before-Trial (PbT) policy, which inefficiently allocates test-time compute by incurring planning overhead even on directly solvable problems. We propose Planning-after-Trial (PaT), an adaptive policy for code generation that invokes a planner only upon verification failure. This adaptive policy naturally enables a heterogeneous model configuration: a cost-efficient model handles generation attempts, while a powerful model is reserved for targeted planning interventions. Empirically, across multiple benchmarks and model families, our approach significantly advances the cost-performance Pareto frontier. Notably, our heterogeneous configuration achieves performance comparable to a large homogeneous model while reducing inference cost by approximately 69\%.
@article{arxiv.2605.07248,
title = {PaT: Planning-after-Trial for Efficient Test-Time Code Generation},
author = {Youngsik Yoon and Sungjae Lee and Seockbean Song and Siwei Wang and Wei Chen and Jungseul Ok},
journal= {arXiv preprint arXiv:2605.07248},
year = {2026}
}