generative ai

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

Vibe Coding (VC) is a form of software development assisted by generative AI, in which developers describe the intended functionality or logic via natural language prompts, and the AI system generates the corresponding source code. VC can be leveraged for rapid prototyping or developing the Minimum Viable Products (MVPs); however, it may introduce several risks throughout the software development life cycle. Based on our experience from several internally developed MVPs and a review of recent industry reports, this article analyzes the flow-debt tradeoffs associated with VC. The flow-debt trade-off arises when the seamless code generation occurs, leading to the accumulation of technical debt through architectural inconsistencies, security vulnerabilities, and increased maintenance overhead. These issues originate from process-level weaknesses, biases in model training data, a lack of explicit design rationale, and a tendency to prioritize quick code generation over human-driven iterative development. Based on our experiences, we identify and explain how current model, platform, and hardware limitations contribute to these issues, and propose countermeasures to address them, informing research and practice towards more sustainable VC approaches.

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

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

Organisations are examining how generative AI can support their operational work and decision-making processes. This study investigates how employees in a energy company understand AI adoption and identify areas where AI and LLMs-based agentic workflows could assist daily activities. Data was collected in four weeks through sixteen semi-structured interviews across nine departments, supported by internal documents and researcher observations. The analysis identified areas where employees positioned AI as useful, including reporting work, forecasting, data handling, maintenance-related tasks, and anomaly detection. Participants also described how GenAI and LLM-based tools could be introduced through incremental steps that align with existing workflows. The study provides an overview view of AI adoption in the energy sector and offers a structured basis for identifying entry points for practical implementation and comparative research across industries.

Survey of AI Tool Usage in Programming Course: Early Observations

Early Results of an AI Multiagent System for Requirements Elicitation and Analysis

LLM-based agents for automating the enhancement of user story quality: An early report

In agile software development, maintaining high-quality user stories is crucial, but also challenging. This study explores the use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams. We developed a reference model for an Autonomous LLM-based Agent System and implemented it at the company. The quality of user stories in the study and the effectiveness of these agents for user story quality improvement was assessed by 11 participants across six agile teams. Our findings demonstrate the potential of LLMs in improving user story quality, contributing to the research on AI role in agile development, and providing a practical example of the transformative impact of AI in an industry setting.

AI and Agile Software Development: From Frustration to Success - XP2025 Workshop Summary

The full-day workshop on AI and Agile at XP 2025 convened a diverse group of researchers and industry practitioners to address the practical challenges and opportunities of integrating Artificial Intelligence into Agile software development. Through interactive sessions, participants identified shared frustrations related to integrating AI into Agile Software Development practices, including challenges with tooling, governance, data quality, and critical skill gaps. These challenges were systematically prioritized and analyzed to uncover root causes. The workshop culminated in the collaborative development of a research roadmap that pinpoints actionable directions for future work, including both immediate solutions and ambitious long-term goals. The key outcome is a structured agenda designed to foster joint industry-academic efforts to move from identified frustrations to successful implementation.

Anomaly detection in smart power grids with graph-regularized MS-SVDD: a multimodal subspace learning approach

Anomaly detection in smart power grids is a critical challenge due to the complexity, heterogeneity, and dynamic nature of sensor data streams. Existing one-class classification methods, particularly Subspace Support Vector Data Description (SVDD), have been extended to multimodal scenarios but often fail to fully exploit the structural dependencies across modalities, limiting their robustness in real-world applications. In this paper, we address this gap by proposing a generalized Multimodal Subspace Support Vector Data Description (MS-SVDD) model with graph-embedded regularization. The method projects data from multiple modalities into a shared low-dimensional subspace while preserving modality-specific structure through Laplacian regularizers. Our approach is evaluated on a three-modality dataset derived from smart grid event time series, using a dedicated preprocessing pipeline for constructing one-class classification training samples. The results demonstrate that our graph-embedded MS-SVDD improves robustness of event detection compared to conventional approaches, highlighting the potential of integrating graph priors with multimodal subspace learning for advancing anomaly detection in critical infrastructure. More broadly, this work contributes to the wider field of AI by illustrating how relational and structural information can be systematically embedded into one-class models, enabling robust learning under complex, high-dimensional, and multimodal conditions.

From Business Meetings to Requirement Artifacts: An Agentic AI Approach with MARARE

This paper presents MARARE, a real-time multi-agent system that transforms meeting dialogues into structured software requirements. One agent interacts with participants, while background agents extract and verify requirements collaboratively. Evaluation using the LLM-as-a-Judge method across five meetings (5–8 minutes each) shows a mean coverage of 80.0 ± 11.2 % (mean ± SD), semantic similarity of 0.86 ± 0.05, and hallucination rate of 14.3 ± 6.2 %. Preliminary results indicate performance differences across LLMs, suggesting that model choice influences coverage, consistency, and hallucination rates.

Bridging Humans and LLMs: Investigating Human-AI Collaboration in Multi-agent Requirements Analysis for Organizational AI Adoption

Context: Organizations adopting Artificial Intelligence (AI) face challenges in eliciting and analyzing requirements that align with strategic objectives, especially when human oversight and iterative refinement are needed. Large Language Models (LLMs)-based Multi-agent systems provide a potential solution by supporting structured and collaborative Requirements Engineering (RE) processes for AI adoption planning. Objective: The objective of this study is to investigate whether a multi-agent system, built on LLMs and supported by human input, can assist in requirements analysis for AI adoption. Method: We used a mixed-method approach: (i) designed and developed a multi-agent system to support the generation and prioritization of requirements for AI adoption, (ii) conducted multiple case studies with four companies to evaluate the system, and (iii) collected data through post-session questionnaires from nine participants and follow-up interviews, one per company. Results: Questionnaire and interview findings together indicate that the system may assist in identifying relevant and goal-aligned requirements. Seven participants considered the generated requirements relevant, and six found them aligned with organizational goals. Participants noted that iterative feedback improved completeness and feasibility, often within two feedback rounds. Both data sources show that human input was essential to clarify technical details, ensure contextual accuracy, and validate prioritization results. Participants from all companies also identified usability, transparency, and scalability as areas requiring further refinement for broader organizational use. Conclusions: LLM-based multi-agent systems can support strategic AI planning by enabling iterative refinement with human experts. Future work will include more interviews with stakeholders and adjustments to system features to improve transparency, usability, and scalability.

Fractal-Wave Algebra Manifesto: Dynamic Arithmetic, Wave-Based Computation, and Prior Art Foundations

This document presents the foundational manifesto of Fractal-Wave Algebra (FWA), a dynamic mathematical and computational paradigm that reframes arithmetic, algebra, and information processing as wave‑based, symmetry‑breaking evolutionary processes. Classical mathematics is described as a static projection of deeper dynamic wave transitions, while FWA introduces a generative ontology where numbers represent quanta of state evolution and algebraic operations correspond to active symmetry‑deformation transitions. The manifesto establishes the philosophical, mathematical, and physical basis of FWA. As stated in the document: “Classical mathematics is fundamentally static… Under FWA, numbers are historical markers of sequential symmetry breaking, and algebraic equations are projections of dynamic state evolution.” It contrasts dynamic arithmetic with classical linear arithmetic, showing that expressions like a + b = c are simplified macro‑projections of deeper wave‑state transitions. The document introduces operators such as Da, Pc, and AS, describing how symmetry deformation collapses into classical arithmetic when AS → 0. The manifesto applies FWA to major scientific paradoxes: P vs NP — demonstrating that NP complexity collapses to polynomial time inside wave‑native photonic hardware through multi‑layered interference and resonance reinforcement. Riemann Hypothesis — interpreting non‑trivial zeros as fractal wave nodes fixed to Re(s)=1/2 due to symmetry‑collapse constraints. The document outlines a technical blueprint for future computing hardware, including photonic integrated circuits, in‑memory wave computing, and wave‑based AI architectures. It emphasizes replacing digital matrix weights with phase‑resonance mappings and diagnosing errors as geometric variations across hierarchical wave levels. The manifesto also includes prior‑art Python code demonstrating self‑similar fractal acceleration for non‑linear data grids: “This document serves as an open-access foundational manifesto establishing prior art for Fractal-Wave Algebra and Dynamic Arithmetic applications…” Overall, this publication establishes the theoretical, computational, and engineering foundations of FWA as a new paradigm for mathematics, quantum computing, and artificial intelligence.

How to Judge the Reliability of AI Responses: A Practical Guide to Context, Memory, Sycophancy, and Verification

This document presents a practical reliability guideline for using generative AI responses in business and everyday decision-making. It is based on a dialogue record in which an AI system was asked to analyze how memory, context, sycophancy, anchoring, and personalization may influence its own responses. The dialogue is not treated as empirical proof. Instead, it is used as an observational source from which a practical verification framework is derived. The central claim of this document is that the reliability of AI responses should not be judged by fluency or confidence, but by the type of question, verifiability, information density in training data, context dependence, and the availability of external validation. Definitions, code generation, structured summaries, translation, and transformations of provided text are relatively high-reliability uses. By contrast, current facts, numerical claims, prices, predictions, philosophical claims, personal intention inference, and AI self-evaluation require independent verification. This work is intended as a practical research note and guide rather than a peer-reviewed empirical study. Its purpose is to help users classify AI responses by reliability level, identify low-reliability signals, and apply verification steps before using AI outputs in business, education, research support, or everyday decision-making.