This paper explores how humans and conversational large language models can collaborate through vibe coding, comparing solo and collaborative interaction models in software development using Test-Driv…

The paper proposes TraceDev, a multi-agent framework for automated software development grounded in use cases, achieving higher success rates than baseline approaches in repository-level code generati…

This paper proposes a new paradigm for human-machine cooperation in software engineering, where machines amplify engineers' reasoning through causation.

AutoACSL is a framework that uses Code Property Graphs and large language models to generate formal specifications for C programs with improved success ratio and full proof ratio.

This paper studies AI development frameworks for software engineering and proposes a six-dimension process taxonomy.

The paper introduces a new structural merge tool that ensures parsability and universality in comparison to existing tools, resulting in fewer incorrect merge results.

This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system…

This paper presents a case study on using AI coding agents in software engineering and develops a process model for governing high-velocity agentic implementation.

This paper proposes a context-aware AI framework for generating telecom test scripts that adapt to fine-grained changes in the system using a delta engine and a knowledge graph.

SEMBridge is a tagless-final framework that allows a single executable object program to generate multiple program semantics, including weakest-precondition and bounded-checking interpretations, ensur…

This paper proposes an automated method to generate complete PDDL planning problems directly from Asset Administration Shell (AAS) capability models, eliminating the need for specialized planning expe…

This paper proposes conversational AI review assistants for code review, systems that engage in conversation with developers instead of just generating comments.

This paper evaluates the improvement of statistical fault localization by augmenting it with execution features.

This paper compares the quality and coverage of epic-organized LLM-generated Gherkin acceptance criteria with requirement-aligned generation, using four requirements documents from the PURE dataset.

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

This paper introduces TRIM, an algorithm that minimizes redundant edits in AI-generated code, called CodeSlop, by minimizing agent trajectories, reducing CodeSlop by 17.9%-32.9% with negligible perfor…

TARS is an LLM-powered agent integrated into Visual Studio Code that provides autonomous explanations anchored directly to the code under analysis, adapting to developers' expertise, role, and stylist…

This paper investigates how developer attributes influence generated software using AI, finding significant differences in interface design, template content, and code structure based on age and gende…