APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911183995404288 |
|---|---|
| author | Zhong, Hua Jiang, Shan Khurshid, Sarfraz |
| author_facet | Zhong, Hua Jiang, Shan Khurshid, Sarfraz |
| contents | APIs are central to modern software development, yet composing new APIs from large libraries is difficult due to the exponential search space; traditional component-based synthesis relies on costly exploration and hand-crafted specifications. While large language models (LLMs) can generate implementations from natural language, hallucinations and limited access to up-to-date contextual information often yield incorrect code. In this paper, we present APRIL, an approach that combines LLM-based synthesis with Automatic Prompt Optimization (APO) and Reinforcement Learning from Verifiable Rewards (RLVR): APO iteratively refines prompts for a frozen model, while RLVR fine-tunes the policy toward functional correctness, producing an efficient synthesis pipeline. Evaluated on 81 real-world APIs from widely used scientific Python libraries and benchmarked against instruction-tuned but unfine-tuned LLMs guided by expert prompts, APRIL achieves substantial improvements. These results indicate that integrating APO and RLVR provides a robust, scalable path for component-based API synthesis in large libraries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning Zhong, Hua Jiang, Shan Khurshid, Sarfraz Software Engineering Artificial Intelligence Machine Learning Programming Languages APIs are central to modern software development, yet composing new APIs from large libraries is difficult due to the exponential search space; traditional component-based synthesis relies on costly exploration and hand-crafted specifications. While large language models (LLMs) can generate implementations from natural language, hallucinations and limited access to up-to-date contextual information often yield incorrect code. In this paper, we present APRIL, an approach that combines LLM-based synthesis with Automatic Prompt Optimization (APO) and Reinforcement Learning from Verifiable Rewards (RLVR): APO iteratively refines prompts for a frozen model, while RLVR fine-tunes the policy toward functional correctness, producing an efficient synthesis pipeline. Evaluated on 81 real-world APIs from widely used scientific Python libraries and benchmarked against instruction-tuned but unfine-tuned LLMs guided by expert prompts, APRIL achieves substantial improvements. These results indicate that integrating APO and RLVR provides a robust, scalable path for component-based API synthesis in large libraries. |
| title | APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning |
| topic | Software Engineering Artificial Intelligence Machine Learning Programming Languages |
| url | https://arxiv.org/abs/2509.25196 |