Automatic Qiskit Code Refactoring Using Large Language Models

• URL: http://arxiv.org/abs/2506.14535v1
• Date: Tue, 17 Jun 2025 14:00:48 GMT
• Title: Automatic Qiskit Code Refactoring Using Large Language Models
• Authors: José Manuel Suárez, Luis Mariano Bibbó, Joaquin Bogado, Alejandro Fernandez,
• Abstract summary: We present a novel methodology for Qiskit code using large language models (LLMs)<n>We begin by extracting a taxonomy of migration scenarios from the different sources of official Qiskit documentation.<n>This taxonomy, along with the original Python source code, is provided as input to an LLM, which is then tasked with identifying instances of migration scenarios in the code.
• Score: 39.71511919246829
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: As quantum software frameworks evolve, developers face increasing challenges in maintaining compatibility with rapidly changing APIs. In this work, we present a novel methodology for refactoring Qiskit code using large language models (LLMs). We begin by extracting a taxonomy of migration scenarios from the different sources of official Qiskit documentation (such as release notes), capturing common patterns such as migration of functionality to different modules and deprecated usage. This taxonomy, along with the original Python source code, is provided as input to an LLM, which is then tasked with identifying instances of migration scenarios in the code and suggesting appropriate refactoring solutions. Our approach is designed to address the context length limitations of current LLMs by structuring the input and reasoning process in a targeted, efficient manner. The results demonstrate that LLMs, when guided by domain-specific migration knowledge, can effectively assist in automating Qiskit code migration. This work contributes both a set of proven prompts and taxonomy for Qiskit code migration from earlier versions to version 0.46 and a methodology to asses the capabilities of LLMs to assist in the migration of quantum code.

Related papers

• CIgrate: Automating CI Service Migration with Large Language Models [2.3020018305241337]
  This report presents a study in which we aim to assess whether CI migration can be improved using Large Language Models (LLMs)<n>LLMs have demonstrated strong capabilities in code generation and transformation tasks.<n>We propose CIgrate, an LLM-based framework for automatically migrating CI configurations.
  arXiv  Detail & Related papers  (2025-07-27T19:51:37Z)
• CODEMENV: Benchmarking Large Language Models on Code Migration [11.735053997817765]
  CODEMENV consists of 922 examples spanning 19 Python and Java packages.<n>It covers three core tasks: identifying functions incompatible with specific versions, detecting changes in function definitions, and adapting code to target environments.<n> Experimental evaluation with seven LLMs on CODEMENV yields an average pass@1 rate of 26.50%, with GPT-4O achieving the highest score at 43.84%.
  arXiv  Detail & Related papers  (2025-06-01T08:29:59Z)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs [54.59207567677249]
  Large language models (LLMs) still struggle across tasks outside of high-resource languages.<n>In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce.
  arXiv  Detail & Related papers  (2025-05-23T20:28:31Z)
• SweRank: Software Issue Localization with Code Ranking [109.3289316191729]
  SweRank is an efficient retrieve-and-rerank framework for software issue localization.<n>We construct SweLoc, a large-scale dataset curated from public GitHub repositories.<n>We show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems.
  arXiv  Detail & Related papers  (2025-05-07T19:44:09Z)
• Using LLMs for Library Migration [1.9247157750972368]
  Large Language Models (LLMs) are good at generating and transforming code and finding similar code.<n>We evaluate three LLMs, LLama 3.1, GPT-4o mini, and GPT-4o on PyMigBench, where we migrate 321 real-world library migrations.<n>LLama 3.1, GPT-4o mini, and GPT-4o correctly migrate 89%, 89%, and 94% of the migration-related code changes respectively.
  arXiv  Detail & Related papers  (2025-04-17T18:32:48Z)
• Migrating Code At Scale With LLMs At Google [0.0]
  We discuss a large-scale, costly and traditionally manual migration project at Google.<n>We propose a novel automated algorithm that uses change location discovery and a Large Language Model (LLM) to aid developers conduct the migration.<n>Our results suggest that our automated, LLM-assisted workflow can serve as a model for similar initiatives.
  arXiv  Detail & Related papers  (2025-04-13T18:52:44Z)
• Open-domain Implicit Format Control for Large Language Model Generation [52.83173553689678]
  We introduce a novel framework for controlled generation in large language models (LLMs) This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality.
  arXiv  Detail & Related papers  (2024-08-08T11:51:45Z)
• Example-Based Automatic Migration of Continuous Integration Systems [2.2836654317217326]
  Continuous Integration (CI) is a widely adopted practice for faster code change integration and testing. Developers often migrate between CI systems in pursuit of features like matrix building or better logging. This migration is effort intensive and error-prone owing to limited knowledge of the new CI system and its syntax. We propose a novel approach for CI system's automatic migration: CIMig.
  arXiv  Detail & Related papers  (2024-07-02T20:19:21Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules [51.82044734879657]
  We propose CodeChain, a novel framework for inference that elicits modularized code generation through a chain of self-revisions. We find that CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests.
  arXiv  Detail & Related papers  (2023-10-13T10:17:48Z)
• Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases [15.964849180459675]
  $k$NM-LM is a retrieval-augmented language model that integrates domain knowledge into language models without fine-tuning. Our approach is able to automatically adapt to different language models and domains.
  arXiv  Detail & Related papers  (2023-08-18T05:25:55Z)

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.