PaT: Planning-after-Trial for Efficient Test-Time Code Generation

ACL ARR 2026 January Submission2278 Authors

Keywords: Code Generation, Test-Time Compute, Adaptive Planning

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\%.

Paper Type: Long

Research Area: Code Models

Research Area Keywords: code models, LLM/AI agents, LLM Efficiency

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English, Python

Submission Number: 2278