作者位次 #2/6ACL 2026Poster· Natural Language Processing
P a T : Planning-after-Trial for Efficient Test-Time Code Generation
Youngsik Yoon · Sungjae Lee · Seockbean Song · Siwei Wang · Wei Chen · Jungseul Ok
摘要
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...