APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning

• URL: http://arxiv.org/abs/2509.25196v1
• Date: Fri, 29 Aug 2025 19:48:09 GMT
• Title: APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning
• Authors: Hua Zhong, Shan Jiang, Sarfraz Khurshid,
• Abstract summary: APRIL combines large language models with Automatic Prompt Optimization (APO) and Reinforcement Learning from Verifiable Rewards (RLVR)<n>APO iteratively refines prompts for a frozen model, while RLVR fine-tunes the policy toward functional correctness, producing an efficient synthesis pipeline.<n> evaluated on 81 real-world APIs from widely used scientific Python libraries.
• Score: 3.4539093004126915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Framework-Aware Code Generation with API Knowledge Graph-Constructed Data: A Study on HarmonyOS [52.483888557864326]
  APIKG4SYN is a framework designed to exploit API knowledge graphs for the construction of API-oriented question-code pairs.<n>We build the first benchmark for HarmonyOS code generation using APIKG4SYN.
  arXiv  Detail & Related papers  (2025-11-29T08:13:54Z)
• Fun-ASR Technical Report [89.84148151617022]
  We present Fun-ASR, a large-scale, LLM-based ASR system that combines massive data, large model capacity, LLM integration, and reinforcement learning.<n>Fun-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements.<n>Thanks to production-oriented optimizations, Fun-ASR achieves state-of-the-art performance on real application datasets, demonstrating its effectiveness and robustness in practical settings.
  arXiv  Detail & Related papers  (2025-09-15T23:19:36Z)
• RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs [3.41612427812159]
  In digital content creation tools, users express their needs through natural language queries that must be mapped to API calls.<n>Existing approaches to synthetic data generation fail to replicate real-world data distributions.<n>We present a novel router-based architecture that generates high-quality synthetic training data.
  arXiv  Detail & Related papers  (2025-05-15T16:53:45Z)
• Pel, A Programming Language for Orchestrating AI Agents [1.223779595809275]
  Pel is a novel programming language designed to bridge the gap between function/tool calling and direct code generation.<n>Inspired by the strengths of Lisp, Elixir, Gleam, and Haskell, Pel provides a syntactically simple, homoiconic, and semantically rich platform.<n>Key features include a powerful piping mechanism for linear composition, first-class closures enabling easy partial application and functional patterns, built-in support for natural language conditions evaluated by LLMs, and an advanced Read-Eval-Print-Loop (REPeL) with Common Lisp-style restarts and LLM-powered helper agents for automated
  arXiv  Detail & Related papers  (2025-04-03T18:46:53Z)
• An approach for API synthesis using large language models [5.222592525740847]
  We present a novel approach of using large language models (LLMs) in API synthesis.<n>LLMs offer a foundational technology to capture developer insights and provide an ideal framework for enabling more effective API synthesis.<n>We perform an experimental evaluation of our approach using 135 real-world programming tasks, and compare it with FrAngel, a state-of-the-art API synthesis tool.
  arXiv  Detail & Related papers  (2025-02-21T06:42:20Z)
• Reinforcement Learning for Long-Horizon Interactive LLM Agents [56.9860859585028]
  Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests.<n>We present a reinforcement learning (RL) approach that trains IDAs directly in their target environments.<n>We derive LOOP, a data- and memory-efficient variant of proximal policy optimization.
  arXiv  Detail & Related papers  (2025-02-03T18:35:42Z)
• Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation [0.0]
  We propose a novel system that integrates Large Language Models (LLMs) for both classifying natural language inputs into corresponding API calls. Our system allows users to invoke complex software functionalities through simple inputs, improving interaction efficiency and lowering the barrier to software utilization.
  arXiv  Detail & Related papers  (2024-09-18T04:56:52Z)
• Octopus: On-device language model for function calling of software APIs [9.78611123915888]
  Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs.
  arXiv  Detail & Related papers  (2024-04-02T01:29:28Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Self-Retrieval: End-to-End Information Retrieval with One Large Language Model [97.71181484082663]
  We introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture. Self-Retrieval internalizes the retrieval corpus through self-supervised learning, transforms the retrieval process into sequential passage generation, and performs relevance assessment for reranking.
  arXiv  Detail & Related papers  (2024-02-23T18:45:35Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.