human-computer interaction

Assessing Small Language Models for Code Generation: An Empirical Study with Benchmarks

This study presents a comprehensive empirical evaluation of 20 open-source Small Language Models and reveals that several compact SLMs achieve competitive results while maintaining a balance between performance and efficiency, making them viable for deployment in resource-constrained environments.

Autonomous Legacy Web Application Upgrades Using a Multi-Agent System

An LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions and maintains context across tasks and agents, improving solution quality over the base model in some cases is proposed.

Vibe Coding in Practice: Flow, Technical Debt, and Guidelines for Sustainable Use

This article analyzes the flow-debt tradeoffs associated with VC and identifies and explains how current model, platform, and hardware limitations contribute to these issues, and proposes countermeasures to address them, informing research and practice towards more sustainable VC approaches.

A Multi-agent LLM System for Automated Requirements Analysis: A Study on User Story Generation and Prioritization

Generative AI Adoption in an Energy Company: Exploring Challenges and Use Cases

This study investigates how employees in a energy company understand AI adoption and identifies areas where AI and LLMs-based agentic workflows could assist daily activities, including reporting work, forecasting, data handling, maintenance-related tasks, and anomaly detection.

A Context-Aware Multi-agent Approach to Enhancing User Story Management in Agile Software Development

Vibe Coding in Software Development: A Multivocal Literature Review

This is one of the first reviews to integrate peer-reviewed and grey literature on vibe coding under a single documented protocol and is strongest for prototyping and user-interface work and weakest for production, data-intensive, and safety-critical use, and tool visibility does not imply effectiveness.

From PDF to Dataset: Semi-Automated Extraction of Fine-Tuning Data

The results indicate that the proposed approach reduces the effort required for manual dataset construction while preserving data quality through mandatory human validation, and highlights the effectiveness of hybrid automation workflows in accelerating fine-tuning dataset preparation without compromising reliability.

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

A variability-preserving imputation method is introduced that augments linear interpolation with locally adaptive stochastic noise, retaining physiological dynamics essential for accurate forecasting in short-term Heart Rate Variability forecasting.

Context Before Code: An Experience Report on Vibe Coding in Practice

An experience report from a small full-stack team that applied contextual prompting and explicit architectural constraints to build a multi-project agent learning platform designed for sustained, production-oriented use and an academic retrieval-augmented generation system is presented.

Epic-Organized vs. Requirement-Aligned Gherkin: An Empirical Evaluation of LLM-Based Acceptance Criteria Generation

Overall, the results suggest that epic-organized generation can improve perceived Gherkin quality while maintaining comparable semantic coverage, although broader replication is needed before generalizing this finding.

Identifying and Prioritizing Generative AI Use Cases in an Organization: An Industrial Case Study

This study investigates how employees in a energy company understand AI adoption and identifies areas where AI and LLMs-based agentic workflows could assist daily activities, including reporting work, forecasting, data handling, maintenance-related tasks, and anomaly detection.