language-specific programming (python/java)

To address the lack of debugging support in polyglot programming—where existing platforms either lack debugging capabilities or incur prohibitive costs to integrate debuggers for new languages—this paper proposes a language-agnostic, dynamically extensible cross-language debugging framework. Built upon the Debug Adapter Protocol (DAP), the framework introduces a novel dynamic pluggable architecture: lightweight, language-specific debug adapters are loaded on-demand at runtime, enabling flexible support for arbitrary language combinations without modifying or reimplementing underlying language debuggers. The design is modular, incorporating language-runtime proxies and inter-process debugging session coordination. Evaluated in a C/JavaScript/Python hybrid environment, the prototype demonstrates manageable code size, low debugging overhead, comprehensive coverage of mainstream polyglot invocation patterns (e.g., foreign function calls, embedded interpreters), and significant improvements in collaborative debugging efficiency and engineering feasibility for multilingual applications.

To address the challenges of simultaneously generating semantically consistent yet stylistically diverse multi-artifact programming exercises—namely source code, test specifications, and natural language descriptions—this paper proposes a compositional generation framework grounded in abstract syntax building blocks. The framework defines reusable syntactic abstractions and integrates templated mapping with multi-objective instantiation to ensure intent preservation and cross-modal co-generation. Its key innovations include: (i) enabling style-controllable, diverse outputs while guaranteeing semantic consistency; and (ii) providing a highly configurable generation interface that substantially reduces customization effort for new tasks. Experimental evaluation demonstrates that the approach outperforms existing baselines across three critical dimensions: generation quality, output diversity, and system extensibility.

This study addresses the unclear human-AI collaboration mechanisms in specification-driven software development with large language models (LLMs). We propose CURRANTE, a structured three-stage collaborative paradigm that guides developers through sequential refinement of requirements specifications, test cases, and function implementations. Implemented as a Visual Studio Code extension, CURRANTE integrates LLM assistance, fine-grained interaction logging, and automated test-based evaluation. By collecting interaction data and multidimensional performance metrics—including pass rates and completion time—on medium-difficulty tasks from LiveCodeBench, our work provides the first systematic empirical analysis of how iterative specification and testing dynamically influence LLM-generated code quality. These findings offer evidence-based insights for designing effective AI-augmented programming environments.

Cross-language design pattern detection suffers from high adaptation costs, poor consistency, and maintenance difficulties due to language-specific analyses. Method: This paper proposes a multi-language detection paradigm based on Virtual Abstract Syntax Trees (Virtual ASTs) and implements it in the tool DP-LARA. Leveraging the LARA multi-language framework, DP-LARA uniformly maps Java and C/C++ source code to a language-agnostic Virtual AST representation, enabling pattern recognition via static analysis and an extensible rule engine. Contribution/Results: To our knowledge, this is the first approach achieving cross-language reuse of design pattern detection logic. Empirical evaluation on Java and C/C++ projects demonstrates high accuracy and strong consistency across languages. Language extension effort decreases by approximately 60%, while maintenance overhead for existing language support is significantly reduced. DP-LARA thus provides an efficient, scalable infrastructure for multi-language software architecture analysis.

Existing design pattern detection tools are predominantly language-specific, hindering consistent identification of pattern instances across multi-language codebases. To address this, we propose DP-LARA—a cross-language design pattern detection approach built upon the LARA framework and a novel virtual Abstract Syntax Tree (vAST). DP-LARA establishes the first unified, language-agnostic pattern matching paradigm by mapping Java and C/C++ source code to semantically equivalent vAST representations, then applying static analysis augmented with an extensible rule engine for precise and consistent pattern instance identification. Experimental evaluation demonstrates that DP-LARA achieves detection accuracy on par with state-of-the-art single-language tools for both Java and C/C++, while significantly improving cross-language result consistency and reducing language adaptation effort by over 60%. This work introduces a scalable, maintainable paradigm for multi-language software architecture analysis.

研究通过在JavaScript和Lua中实现Processing/p5，提出了一套软件决策指导原则，以解决不同编程语言环境下创意编码的一致性问题。

研究分析了1000个GitHub仓库中Python库和框架对类型提示的采用、维护情况，通过提取类型注解等方法探讨其使用模式及演变。

Existing log generation methods are predominantly evaluated in monolingual settings, leaving their cross-lingual effectiveness unclear. This work constructs a multilingual logging benchmark comprising 150,000 instances across five programming languages and presents the first systematic evaluation of three state-of-the-art approaches and five large language models in cross-lingual log generation. The study reveals significant disparities in logging difficulty across languages, attributed to language-specific logging insertion patterns and idioms, underscoring the need for tailored multilingual logging strategies. Experimental results demonstrate that UniLog achieves the strongest overall performance, with JavaScript proving more amenable to log generation than Python, which poses greater challenges. Moreover, merely scaling model size or training data yields limited gains in multilingual logging efficacy.

本文解决了细粒度代码重构自动化问题，通过形式化五种Move Statement重构方法，并结合现有技术实现更细粒度的表达式移动。

本文提出了一种基于Eclipse JDT API的自动重构工具，通过引入辅助布尔变量转换含有break和continue语句的Java代码结构，以改善代码结构并支持进一步的自动化重构。