@inproceedings{yoon2026pat,
author = {Yoon, Youngsik and Lee, Sungjae and Song, Seockbean and Wang, Siwei and Chen, Wei and Ok, Jungseul},
title = {PaT: Planning-after-Trial for Efficient Test-Time Code Generation},
booktitle = {The 64th Annual Meeting of the Association for Computational Linguistics (ACL), Main Conference},
year = {2026},
month = {July},
abstract = {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%.},
url = {http://approjects.co.za/?big=en-us/research/publication/pat-planning-after-trial-for-efficient-test-time-code-generation/},
}