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

This paper conducts rapid reviews of peer-reviewed publications to assess the availability of evidence on software engineering practices in government agencies.

This paper introduces ASE-26, a comprehensive undergraduate curriculum designed to formalize and teach agentic software engineering as a distinct academic discipline.

This paper introduces Aleena, an open-source lifecycle alignment agent that uses GitHub to align research software engineering stakeholders and preserve decision continuity.

This paper evaluates Centaur, a foundation model trained on psychological experiments, for program comprehension tasks and compares its performance to Llama 3.1.

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 presents an empirical investigation on the distribution, evolution, and maintenance implications of Domain-Driven Design (DDD) building blocks in open-source GitHub repositories.

The paper proposes projectional decoding, a novel framework that integrates a partial graph model alongside text generation to ensure the semantic validity of LLM-generated software artifacts.

This paper proposes a role-based agentic workflow for vulnerability analysis and mitigation in software engineering, integrating an analyzer agent with CodeQL and evaluating its performance on 25 real…

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

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

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 argues that current Software Bills of Materials (SBOMs) are fundamentally flawed due to a lack of shared understanding regarding what constitutes a 'component,' demonstrating that existing t…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

This paper explores the causes of inconsistent vulnerability scanner findings in the open-source ecosystem.

This paper presents Forge, a pipeline that uses formal verification to ensure the safety and certification of LLM-generated Java code.

This paper presents a software ecosystem enabling consistent development environments for running workflows across diverse hardware platforms.

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…