软件工程
Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O…
Automated testing is crucial for maintaining open-source software quality. However, motivating contributors to include tests for code changes remains a challenge. While existing interventions, such as code coverage metrics and reviewer…
Test cases are essential for software development and maintenance. In practice, developers derive multiple test cases from an implicit pattern based on their understanding of requirements and inference of diverse test scenarios, each…
Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in performance requirements and uncertainty of human cognition…
Large language models have shown remarkable ability in serial code generation, but they still struggle with parallel code for which training data is comparatively scarce. A common remedy is to use coding agents that interact with external…
Context. Behaviour-Driven Development (BDD) suites in Gherkin accumulate step-text duplication with documented maintenance cost. Prior detectors either require runnable tests or are single-organisation, leaving a gap: a static,…
Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual work with complex and expensive analysis tools. In this…
The emergence of vibe coding, a paradigm where non-technical users instruct Large Language Models (LLMs) to generate executable codes via natural language, presents both significant opportunities and severe risks for the construction…
AI coding tools are widely adopted, but most teams plateau at prompt-and-review without a framework for systematic progression. This paper presents the AI Codebase Maturity Model (ACMM), a 6-level framework describing how codebases evolve…
Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling paradigm that shifts the…
Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from critical limitations in code generation, where upfront…
AI coding assistants are now widely used in software development. Software developers increasingly integrate AI-generated code into their codebases to improve productivity. Prior studies have shown that AI-generated code may contain code…
Quantum computing is increasingly practiced through programming, yet most educational offerings emphasize algorithmic or framework-level use rather than software engineering concerns such as testing, abstraction, tooling, and lifecycle…
Large Language Models (LLMs) have revolutionized intelligent application development. While standalone LLMs cannot perform any actions, LLM agents address the limitation by integrating tools. However, debugging LLM agents is difficult and…
Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain specialization methods for LLMs to learn and utilize domain knowledge and data. However, existing…
Efficient implementation of nonlinear model predictive control (NMPC) for bioprocesses remains challenging because large nonlinear models are difficult to organize, simulate, and embed within optimization and control workflows. This…
Getting language models to reason correctly about code requires training on data where each reasoning step can be checked. Current synthetic Chain-of-Thought (CoT) training data often consists of plausible-sounding explanations generated by…
Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Mermaid sequence diagrams for software engineering. However, the lack of existing benchmarks to assess…
Context: Large language models (LLMs) are increasingly used to screen literature for systematic reviews (SRs), but the standard confusion-matrix metrics used to evaluate them can mislead under the imbalanced, cost-asymmetric conditions of…
Commit messages play a key role in documenting the intent behind code changes. However, they are often low-quality, vague, or incomplete, limiting their usefulness. Commit Message Generation (CMG) aims to automatically generate descriptive…