# APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.25196 · HTML: https://mlsanity.com/paper/2509.25196/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 16 of 16)

- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Jigsaw: Large Language Models meet Program Synthesis](https://mlsanity.com/paper/2112.02969/) (2021)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)
- [Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?](https://mlsanity.com/paper/2310.01831/) (2023)
- [TF-Coder: Program Synthesis for Tensor Manipulations](https://mlsanity.com/paper/2003.09040/) (2020)
- [Component-based Synthesis of Table Consolidation and Transformation Tasks from Examples](https://mlsanity.com/paper/1611.07502/) (2016)
- [FrAngel: Component-Based Synthesis with Control Structures](https://mlsanity.com/paper/1811.05175/) (2018)
- [On the Effectiveness of Large Language Models in Writing Alloy Formulas](https://mlsanity.com/paper/2502.15441/) (2025)
- [Generating executable oracles to check conformance of client code to requirements of JDK Javadocs using LLMs](https://mlsanity.com/paper/2411.01789/) (2024)
- [How is Google using AI for internal code migrations?](https://mlsanity.com/paper/2501.06972/) (2025)
- [CASCADE: LLM-Powered JavaScript Deobfuscator at Google](https://mlsanity.com/paper/2507.17691/) (2025)
- [An approach for API synthesis using large language models](https://mlsanity.com/paper/2502.15246/) (2025)
- [Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning](https://mlsanity.com/paper/2405.03509/) (2024)

## Abstract (arXiv)

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.