#Software Engineering
Latest news articles tagged with "Software Engineering". Follow the timeline of events, related topics, and entities.
Articles (22)
-
๐บ๐ธ EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization
[USA]
arXiv:2602.22368v1 Announce Type: cross Abstract: Code summarization is the task of generating natural language descriptions of source code, which is critical for software comprehension and maintenan...
Related: #AI Research, #Human-Computer Interaction -
๐บ๐ธ Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents
[USA]
arXiv:2602.22402v1 Announce Type: cross Abstract: As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codeba...
Related: #Artificial Intelligence, #Computer Science -
๐บ๐ธ Automating the Detection of Requirement Dependencies Using Large Language Models
[USA]
arXiv:2602.22456v1 Announce Type: cross Abstract: Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin criti...
Related: #Artificial Intelligence, #Natural Language Processing -
๐บ๐ธ A Problem-Oriented Perspective and Anchor Verification for Code Optimization
[USA]
arXiv:2406.11935v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities in solving various programming tasks, such as code generation. However, their...
Related: #Code Optimization, #Large Language Models -
๐บ๐ธ CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
[USA]
arXiv:2602.20213v1 Announce Type: cross Abstract: The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benc...
Related: #Artificial Intelligence, #Cybersecurity -
๐บ๐ธ Wink: Recovering from Misbehaviors in Coding Agents
[USA]
arXiv:2602.17037v1 Announce Type: cross Abstract: Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engine...
Related: #Artificial Intelligence, #HumanโComputer Interaction, #Large Language Models, #Autonomous Coding Agents -
๐บ๐ธ OpenSage: Self-programming Agent Generation Engine
[USA]
arXiv:2602.16891v1 Announce Type: new Abstract: Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents...
Related: #Artificial Intelligence, #Agent Development, #Large Language Models, #Automated Tool Generation -
๐บ๐ธ Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary
[USA]
arXiv:2510.19692v2 Announce Type: replace-cross Abstract: Agentic AI is poised to usher in a seismic paradigm shift in Software Engineering (SE). As technologists rush head-along to make agentic AI a...
Related: #Agentic AI, #Socioโtechnical Systems, #Research Frameworks, #Emergent Technologies -
๐บ๐ธ Predicting Open Source Software Sustainability with Deep Temporal Neural Hierarchical Architectures and Explainable AI
[USA]
arXiv:2602.09064v2 Announce Type: replace-cross Abstract: Open Source Software (OSS) projects follow diverse lifecycle trajectories shaped by evolving patterns of contribution, coordination, and comm...
Related: #Machine Learning, #Explainable AI, #Open Source Sustainability, #DataโDriven Analytics -
๐บ๐ธ CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
[USA]
arXiv:2602.07080v1 Announce Type: cross Abstract: Current paradigms for code verification rely heavily on external mechanisms-such as execution-based unit tests or auxiliary LLM judges-which are ofte...
Related: #Artificial Intelligence, #Model Interpretability -
๐บ๐ธ Root Cause Analysis Method Based on Large Language Models with Residual Connection Structures
[USA]
arXiv:2602.08804v1 Announce Type: new Abstract: Root cause localization remain challenging in complex and large-scale microservice architectures. The complex fault propagation among microservices and...
Related: #Artificial Intelligence, #Microservices -
๐บ๐ธ GEBench: Benchmarking Image Generation Models as GUI Environments
[USA]
arXiv:2602.09007v1 Announce Type: new Abstract: Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. ...
Related: #Artificial Intelligence, #Computer Vision -
๐บ๐ธ Artificial Intelligence in Open Source Software Engineering: A Foundation for Sustainability
[USA]
arXiv:2602.07071v1 Announce Type: cross Abstract: Open-source software (OSS) is foundational to modern digital infrastructure, yet this context for group work continues to struggle to ensure sufficie...
Related: #Artificial Intelligence, #Open Source -
๐บ๐ธ Towards Understanding What State Space Models Learn About Code
[USA]
arXiv:2602.06774v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as an efficient alternative to the transformer architecture. Recent studies show that SSMs can match or surpass ...
Related: #Artificial Intelligence, #Machine Learning -
๐บ๐ธ SVRepair: Structured Visual Reasoning for Automated Program Repair
[USA]
arXiv:2602.06090v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown strong potential for Automated Program Repair (APR), yet most existing approaches remain unimodal an...
Related: #Artificial Intelligence, #Computer Vision -
๐บ๐ธ AgentStepper: Interactive Debugging of Software Development Agents
[USA]
arXiv:2602.06593v1 Announce Type: cross Abstract: Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solvin...
Related: #Artificial Intelligence, #Debugging -
๐บ๐ธ Rethinking the effects of data contamination in Code Intelligence
[USA]
arXiv:2506.02791v3 Announce Type: replace-cross Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread...
Related: #Artificial Intelligence, #Data Integrity -
๐บ๐ธ Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
[USA]
arXiv:2504.20406v2 Announce Type: replace Abstract: Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming exper...
Related: #Artificial Intelligence, #Automation -
๐บ๐ธ PromptPex: Automatic Test Generation for Language Model Prompts
[USA]
arXiv:2503.05070v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are being used in many applications and prompts for these models are integrated into software applications as co...
Related: #Artificial Intelligence, #Quality Assurance -
๐บ๐ธ Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
[USA]
arXiv:2601.18282v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in function calling for autonomous agents, yet current mechanisms lack expli...
Related: #Artificial Intelligence, #Machine Learning -
๐บ๐ธ Coding Agents with Environment Interaction: A Theoretical Perspective
[USA]
arXiv:2602.06098v1 Announce Type: cross Abstract: Coding agents are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction stra...
Related: #Artificial Intelligence, #Computer Science Theory -
๐บ๐ธ Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes
[USA]
arXiv:2602.05780v1 Announce Type: cross Abstract: Code completion (CC) is a task frequently used by developers when working in collaboration with LLM-based programming assistants. Despite the increas...
Related: #Artificial Intelligence, #Enterprise Solutions