{"ID":2861857,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00501","arxiv_id":"2510.00501","title":"CodeChemist: Functional Knowledge Transfer for Low-Resource Code Generation via Test-Time Scaling","abstract":"Code Large Language Models (CodeLLMs) are increasingly used in code generation tasks across a wide range of applications. However, their performance is often inconsistent across different programming languages (PLs), with low-resource PLs suffering the most due to limited training data. In this paper, we present CodeChemist, a novel and efficient framework for test-time scaling that enables functional knowledge transfer from high-resource to low-resource PLs using generated test cases. CodeChemist first generates and executes code in high-resource PLs to create test cases that encapsulate functional knowledge. It then uses multi-temperature hedged sampling to generate code snippets in the low-resource PL and selects the best one based on the pass rate of the test cases. Our extensive experiments show that CodeChemist outperforms existing test-time scaling approaches, boosting the performance of code generation for low-resource PLs without requiring any model retraining.","short_abstract":"Code Large Language Models (CodeLLMs) are increasingly used in code generation tasks across a wide range of applications. However, their performance is often inconsistent across different programming languages (PLs), with low-resource PLs suffering the most due to limited training data. In this paper, we present CodeCh...","url_abs":"https://arxiv.org/abs/2510.00501","url_pdf":"https://arxiv.org/pdf/2510.00501v1","authors":"[\"Kaixin Wang\",\"Tianlin Li\",\"Xiaoyu Zhang\",\"Aishan Liu\",\"Xianglong Liu\",\"Ziqi Liu\",\"Zhiqiang Zhang\",\"Jun Zhou\",\"and Bin Shi\"]","published":"2025-10-01T04:33:53Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}