167 papers
This paper introduces Graphectory, a graph-based framework for analyzing the stochastic execution trajectories of agentic software systems, which reveals that richer prompts and stronger models yield more complex reasoning patterns while enabling real-time monitoring and intervention that significantly improves problem resolution rates and efficiency.
KCoEvo is a knowledge graph-augmented framework that addresses the challenges of API-driven code evolution by decomposing migration into path retrieval and informed generation stages, significantly improving accuracy and execution success over standard LLM baselines through structured reasoning and synthetic supervision.
This paper evaluates the security and quality of code generated by Large Language Models across multiple programming languages using a 200-task dataset, revealing that while LLMs can automate coding, they often fail to adopt modern security features and rely on outdated practices, particularly in languages like C++ and Java 17.
DevBench is a realistic, telemetry-driven benchmark comprising 1,800 instances across six languages that evaluates LLMs on code completion tasks with a focus on ecological validity, contamination-free assessment, and detailed diagnostic insights to guide practical model selection and development.
The paper introduces PostTrainBench, a benchmark evaluating the ability of autonomous AI agents to automate LLM post-training under strict compute constraints, revealing that while frontier agents can outperform official models in specific targeted scenarios, they generally lag behind and exhibit concerning failure modes such as reward hacking and unauthorized data usage.
GraphSkill is an agentic framework that improves complex graph reasoning by leveraging hierarchical document retrieval and self-debugging with generated test cases, validated on a new comprehensive dataset.
This paper introduces OODEval, a new benchmark and the CLUE metric set to evaluate large language models on object-oriented design tasks, revealing that while top models approach undergraduate performance, they still lag behind expert designers due to significant semantic deficiencies in generating methods and relationships.
This paper introduces Compiler.next, a novel search-based compiler that transforms human intents into working software by dynamically optimizing cognitive architectures and model parameters to balance accuracy, cost, and latency, thereby advancing the vision of AI-native Software Engineering 3.0.
This quasi-experiment demonstrates that while large language models like Claude and Llama can effectively generate high-quality, human-readable Gherkin specifications from food-safety regulations, their tendency to produce omissions and hallucinations necessitates systematic human oversight in safety-critical domains.
This paper introduces RightTyper, a novel hybrid tool that combines execution-based observations with static analysis and adaptive sampling to generate accurate Python type annotations with significantly lower runtime overhead and higher precision than existing static, dynamic, or AI-based approaches.
This paper introduces PromCopilot, a Large Language Model-based framework that simplifies metric querying in cloud-native systems by transforming natural language questions into PromQL queries through synergistic reasoning with a knowledge graph, achieving 69.1% accuracy on the first manually constructed text-to-PromQL benchmark dataset.
STADA is a specification-based testing framework that systematically generates diverse autonomous driving scenarios from formal temporal logic specifications, achieving significantly higher coverage with far fewer simulations compared to existing template-based or random generation methods.
This paper investigates how individual traits, life circumstances, and project dynamics influence student developers' perceptions of sentiment in text-based messages, revealing that such perceptions are moderately stable, highly dependent on statement ambiguity, and only weakly correlated with specific predictors, thereby suggesting caution in interpreting sentiment analysis outputs.
This paper introduces a collaborative, AI-integrated agile education platform designed to bridge the gap between academic research and industry practice by generating timely, practice-relevant evidence through structured project-based learning and stakeholder engagement.
This paper proposes an agentic framework that leverages Large Language Models and AI agents to transform the static ESG reporting lifecycle into a dynamic, adaptive system capable of automating data extraction, verification, and report generation while addressing challenges like unstructured data and inconsistent terminology.
This paper summarizes the inaugural QuantumX track at JISBD 2025, which united Spanish research groups to explore the integration of software engineering principles with quantum computing, fostered national and Ibero-American collaborations, and outlined future challenges for the emerging discipline of Quantum Software Engineering.
This paper presents FP-Predictor, a Graph Convolutional Network model that leverages Code Property Graphs to effectively predict false positives in Static Application Security Testing reports, achieving high accuracy on benchmarks while demonstrating security-aware reasoning despite limitations in interprocedural control-flow representation.
This paper proposes a paradigm shift from costly software verification to model-free "herding" by leveraging the "Sparsity of Influence" to introduce EZR, a stochastic learner that achieves 90% of peak performance with only 32 samples by directly identifying the few variables that control complex software systems.
This paper introduces the novel concept of Ethically Sourced Code Generation (ES-CodeGen) as a framework for managing the entire lifecycle of code generation models through ethical and sustainable practices, establishing an 11-dimension taxonomy and identifying key consequences through a comprehensive literature review and practitioner survey.
This paper argues that integrating Artificial Intelligence, particularly through Machine Learning and Natural Language Processing, acts as a catalyst for innovation in software engineering by automating tedious tasks and enhancing Agile practices to better manage evolving requirements while maintaining quality and speed.