Accelerating Requirements Specification Using Large Language Models and Retrieval Augmented Generation – A Case Study

Bridging the gap between informal, imprecise, and vague user requirements descriptions and precise formalized specifications is the main task of requirements engineering. Techniques such as interviews or story telling are used when requirements engineers try to identify a user's needs. The requirements specification process is typically done in a dialogue between users, domain experts, and requirements engineers. In our research, we aim at automating the specification of requirements. The idea is to distinguish between untrained users and trained users, and to exploit domain knowledge learned from previous runs of our system. We let untrained users provide unstructured natural language descriptions, while we allow trained users to provide examples of behavioral descriptions. In both cases, our goal is to synthesize formal requirements models similar to statecharts. From requirements specification processes with trained users, behavioral ontologies are learned which are later used to support the requirements specification process for untrained users. Our research method is original in combining natural language processing and search-based techniques for the synthesis of requirements specifications. Our work is embedded in a larger project that aims at automating the whole software development and deployment process in envisioned future software service markets.

Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities

Building and delivering high-quality software is critical in software engineering and requires verification and validation processes for end-to-end testing that are reliable, robust, and deliver correct results fast. Manual testing of LLM models, while feasible, is very time-consuming and inefficient and has scalability issues depending on how big the model under test (MUT) is. Recent research and cutting-edge technology innovations in LLM models have deeply influenced software engineering. We need to integrate its impact robustly in areas of model analysis, test automation, model execution, debugging, and report generation.This paper focuses on a framework approach for automated software testing of the LLM models to reduce human interactions and has improved results in a fast, cost-efficient, and time-efficient manner for automated testing methods for industries. The proposed Automation Framework (LLMAutoE2E) leverages and integrates LLMs for testing of different LLM models (like BERT, BART, Hugging Face, and multiple models available to test) to automate the end-to-end execution lifecycle of the LLM models. By leveraging LLMs, companies and industries can generate automated test cases, automated unit test codes, automated integration and end-to-end tests, and automated reporting of the LLM model's execution results. This research emphasizes the potential of the Automation Framework (LLMAutoE2E) for LLM to automate and streamline the overall execution and result generation of the LLM models and the overall testing workflows while addressing challenges in current LLM models testing, its accuracy and scalability for deployments, and reporting. The proposed Automation Framework (LLMAutoE2E) can also automate defect analysis, which improves the software reliability by a manifold and reduces the development cycles for companies. This Research paper details the role of Automation Frameworks for LLMs and how it is transforming QA processes, key methodologies, improving reliability and efficiency, addressing current challenges like model safety, bias detection, and continuous monitoring, and future trends in AI-driven software testing.

Generative AI systems based on Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering tasks, from code generation to natural language processing. However, a significant gap persists between curated demonstrations and production-grade deployment. This technical report presents a practitioner-driven analysis of LLM limitations encountered during sustained, real-world use across software development workflows. Drawing from multiple case studies—including natural-language-driven development (“vibe coding”), API integration, multi-file refactoring, and general-purpose question answering—we identify and taxonomize four critical failure modes: (1) the Complexity Cliff, where LLM performance degrades non-linearly as task interdependency grows; (2) Context Window Blindness, where finite attention spans cause silent contract violations across distributed codebases; (3) the Memory Illusion, where session discontinuity erases accumulated architectural knowledge; and (4) Confident Hallucination, where models generate plausible but fabricated outputs indistinguishable in tone from correct ones. We formalize the Verification Paradox—an inverse relationship between a user’s need for AI assistance and their capacity to validate its outputs—and propose a practical five-strategy framework for effective human–AI collaboration in software engineering contexts. We further introduce the concept of Contextual Reasoning Failure, evidenced by cases where LLMs optimize for literal query patterns while ignoring situational logic obvious to any human observer. Our findings suggest that current LLMs, while powerful pattern-matching engines, lack the contextual reasoning, persistent memory, and epistemic self-awareness necessary for reliable autonomous operation, and that practitioner expertise remains the critical safeguard against AI-induced defects in production systems.

The significant advancements in Large Language Models (LLMs) have resulted in their widespread adoption across various tasks within Software Engineering (SE), including vulnerability detection and repair. Numerous studies have investigated the application of LLMs to enhance vulnerability detection and repair tasks. Despite the increasing research interest, there is currently no existing survey that focuses on the utilization of LLMs for vulnerability detection and repair. In this paper, we aim to bridge this gap by offering a systematic literature review of approaches aimed at improving vulnerability detection and repair through the utilization of LLMs. The review encompasses research work from leading SE, AI, and Security conferences and journals, encompassing 43 papers published across 25 distinct venues, along with 15 high-quality preprint papers, bringing the total to 58 papers. By answering three key research questions, we aim to (1) summarize the LLMs employed in the relevant literature, (2) categorize various LLM adaptation techniques in vulnerability detection, and (3) classify various LLM adaptation techniques in vulnerability repair. Based on our findings, we have identified a series of limitations of existing studies. Additionally, we have outlined a roadmap highlighting potential opportunities that we believe are pertinent and crucial for future research endeavors.

The precise identification of plant pests and diseases plays a crucial role in preserving crop health and optimizing agricultural productivity. In practice, however, farmers frequently report symptoms in informal, everyday language. Traditional intelligent farming assistants are built upon domain-specific classification frameworks that depend on formal terminologies and structured symptom inputs, leading to subpar performance when faced with natural, unstructured farmer descriptions. To address this issue, we propose an innovative approach that classifies plant pests and diseases from colloquial symptom reports by leveraging soft prompt-tuning. Initially, we utilize Pretrained Language Models (PLMs) to conduct named entity recognition and retrieve domain-specific knowledge to enrich the input. Notably, this knowledge enrichment process introduces a kind of semantic alignment between the colloquial input and the acquired knowledge, enabling the model to better align informal expressions with formal agricultural concepts. Next, we apply a soft prompt-tuning strategy coupled with an external knowledge enhanced verbalizer for the classification task. The experimental results demonstrate that the proposed method outperforms baseline approaches, including state-of-the-art(SOTA) large language models (LLMs), in classifying plant pests and diseases from informal farmer descriptions. These results highlight the potential of prompt-tuning methods in bridging the gap between informal descriptions and expert knowledge, offering practical implications for the development of more accessible and intelligent agricultural support systems.

The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in a variety of application domains, including cybersecurity. As the volume and sophistication of cyber threats continue to grow, there is an increasing need for intelligent systems that can automatically detect vulnerabilities, analyze malware, and respond to attacks. In this survey, we conduct a comprehensive review of the literature on the application of LLMs in cybersecurity (LLM4Security). By comprehensively collecting over 40K relevant papers and systematically analyzing 185 papers from top security and software engineering venues, we aim to provide a holistic view of how LLMs are being used to solve diverse problems across the cybersecurity domain. Through our analysis, we identify several key findings. First, we observe that LLMs are being applied to an expanding range of cybersecurity tasks, including vulnerability detection, malware analysis, and network intrusion detection. Second, we analyze application trends of different LLM architectures (such as encoder-only, encoder-decoder, and decoder-only) across security domains. Third, we identify increasingly sophisticated techniques for adapting LLMs to cybersecurity, such as advanced fine-tuning, prompt engineering, and external augmentation strategies. A significant emerging trend is the use of LLM-based autonomous agents, which represent a paradigm shift from single-task execution to orchestrating complex, multi-step security workflows. Furthermore, we find that the datasets used for training and evaluating LLMs are often limited, highlighting the need for more comprehensive datasets and the use of LLMs for data augmentation. Finally, we discuss the main challenges and opportunities for future research, including the need for more interpretable models, addressing the inherent security risks of LLMs, and their potential for proactive defense. Overall, our survey provides a comprehensive overview of the current state-of-the-art in LLM4Security and identifies several promising directions for future research. We believe that the insights and findings presented in this survey will contribute to the growing body of knowledge on the application of LLMs in cybersecurity and provide valuable guidance for researchers and practitioners working in this field.

Large language models (LLMs) are quickly being adopted in a wide range of learning experiences, especially via ubiquitous and broadly accessible chat interfaces like ChatGPT. This type of interface is readily available to students and teachers around the world. Coding education is an interesting test case, both because LLMs have strong performance on coding tasks, and because LLM-powered support tools are rapidly becoming part of the workflow of professional software engineers. To help understand the impact of generic LLM use on coding education, we conducted a large-scale randomized control trial with 5,831 students from 146 countries in an online coding class in which we provided some students with access to a chat interface with GPT-4. Under some assumptions, we estimate positive benefits on exam performance for adopters, the students who used the tool, but over all students, the advertisement of GPT-4 led to a significant average decrease in exam participation. We observe similar decreases in other forms of course engagement. However, this decrease is modulated by the student's country of origin. Offering access to LLMs to students from low human development index countries increased their exam participation rate on average. Our results suggest there may be promising benefits to using LLMs in an introductory coding class, but also potential harms for engagement, which makes their longer term impact on student success unclear. Our work highlights the need for additional investigations to help understand the potential impact of future adoption and integration of LLMs into classrooms.

With the rapid advancement of large language models (LLMs), code translation has become a critical yet challenging task in software engineering. Existing evaluations of this task remain unreliable due to two key limitations: the absence of specialized function-level code translation benchmarks and flawed evaluation pipelines. Specifically, current pipelines lack post-processing mechanisms to extract target code from LLMs’ inherently unstable output formats, directly resulting in non-executable translations and false negatives in evaluation. To address these issues, we introduce FuncTransEval, an enhanced multilingual benchmark. It comprises 400×4 functions across four programming languages (Python, C++, Java, and JavaScript) and 12 bidirectional translation pairs, each paired with executable unit tests for fine-grained functional validation. Using FuncTransEval, we systematically assess LLMs’ true capabilities in code translation and identify their core limitations: inadequate understanding of the implicit information such as function logic, type specifications, and cross-language differences. To mitigate these shortcomings, we propose ICAM-Trans (Implicit-Context-Aware Multi-Agent Framework for function-level code translation). ICAM-Trans is a hierarchical, autonomous multi-agents architecture that explicitly uncovers and leverages these implicit contextual information during translation. It employs a Translation Orchestrate Agent (TOA) to autonomously coordinate four specialized Context Analysis Agents (CAAs), which conduct pre-translation analyses on different aspects. Insights from these analyses guide a Context-Aware Translation Agent (CTA) to generate semantically faithful target code. Experiments on FuncTransEval demonstrate that ICAM-Trans consistently outperforms strong baselines, validating its effectiveness in achieving high-fidelity and interpretable function-level code translation.

Impact of code context and prompting strategies on automated unit test generation with modern general-purpose large language models

Large Language Models (LLMs) have demonstrated remarkable effectiveness across various domain-specific applications. However, which fundamental capabilities most contribute to their success in different domains remains unclear. This uncertainty complicates LLM evaluation, as existing benchmark-based assessments often fail to capture their real-world performance, where the required capabilities may differ from those measured in the benchmarks. In this survey, we provide a systematic introduction to LLMs’ fundamental capabilities, encompassing their definitions, formation mechanisms, and practical applications. We further explore the relationships among these capabilities and discuss how they collectively support complex problem-solving in domain-specific applications. Building on this foundation, we review recent advances in LLM-driven applications across nine specific domains: medicine, law, computational biology, finance, social sciences and psychology, computer programming and software engineering, robots and agents, AI for disciplines, and creative work. We analyze how specific capabilities are leveraged for each domain to address unique requirements. This perspective enables us to establish connections between these capabilities and domain requirements, and to evaluate the varying importance of different capabilities across different domains. Based on these insights, we propose evaluation strategies tailored to the essential capabilities required in each domain, offering practical guidance for selecting suitable backbone LLMs in real-world applications.

This scientific article presents the results of a study focused on the current practices and future prospects of AI-tools usage, specifically large language models (LLMs), in software development (SD) processes within European IT companies. The Pan-European study covers 35 SD teams from all regions of Europe and consists of three sections: the first section explores the current adoption of AI-tools in software production, the second section addresses common challenges in LLMs implementation, and the third section provides a forecast of the tech future in AI-tools development for SD. The study reveals that AI-tools, particularly LLMs, have gained popularity and approbation in European IT companies for tasks related to software design and construction, coding, and software documentation. However, their usage for business and system analysis remains limited. Nevertheless, challenges such as resource constraints and organizational resistance are evident. The article also highlights the potential of AI-tools in the software development process, such as automating routine operations, speeding up work processes, and enhancing software product excellence. Moreover, the research examines the transformation of IT paradigms driven by AI-tools, leading to changes in the skill sets of software developers. Although the impact of LLMs on the software development industry is perceived as modest, experts anticipate significant changes in the next 10 years, including AI-tools integration into advanced IDEs, software project management systems, and product management tools. Ethical concerns about data ownership, information security and legal aspects of AI-tools usage are also discussed, with experts emphasizing the need for legal formalization and regulation in the AI domain. Overall, the study highlights the growing importance and potential of AI-tools in software development, as well as the need for careful consideration of challenges and ethical implications to fully leverage their benefits.

As software applications get increasingly connected and complex, cybersecurity becomes more and more important to consider during development and evaluation. Software engineers need to be aware of various security threats and the countermeasures that can be taken to mitigate them. Currently, there is a lack of guidance for software engineers aiming to develop secure web applications. We conducted a design science research study, resulting in a set of guidelines to aid software engineers in developing secure web applications. The set of guidelines was constructed based on interview data with 10 industry practitioners. These guidelines were then evaluated using a survey with 28 respondents. Additionally, we conducted experiments in which we provided a large language model with our guidelines and vulnerability reports as input. The large language model should extend the given vulnerability reports by recommending which of our guidelines can help prevent the given vulnerability in the future. The extended reports were evaluated by two external researchers experienced in cyber security and one author. Our results indicate that developers consider using these proposed guidelines for the development and assessment of secure web applications in different stages of the software development lifecycle. Our results also show that it is possible to automatically enhance vulnerability reports to support developers meaningfully and that the guidelines recommended by the large language model are useful to prevent the respective vulnerabilities in the future.

Software development involves collaborative interactions where stakeholders express opinions across various platforms. Recognizing the sentiments conveyed in these interactions is crucial for the effective development and ongoing maintenance of software systems. For software products, analyzing the sentiment of user feedback, e.g., reviews, comments, and forum posts can provide valuable insights into user satisfaction and areas for improvement. This can guide the development of future updates and features. However, accurately identifying sentiments in software engineering datasets remains challenging. This study investigates bigger large language models (bLLMs) in addressing the labeled data shortage that hampers fine-tuned smaller large language models (sLLMs) in software engineering tasks. We conduct a comprehensive empirical study using five established datasets to assess three open source bLLMs in zero-shot and few-shot scenarios. Additionally, we compare them with fine-tuned sLLMs, using sLLMs to learn contextual embeddings of text from software platforms. Our experimental findings demonstrate that bLLMs exhibit state-of-the-art performance on datasets marked by limited training data and imbalanced distributions. bLLMs can also achieve excellent performance under a zero-shot setting. However, when ample training data are available or the dataset exhibits a more balanced distribution, fine-tuned sLLMs can still achieve superior results.

Artificial intelligence and recent advances in deep learning architectures, including transformer networks and large language models, change the way people think and act to solve problems. Software engineering, as an increasingly complex process to design, develop, test, deploy, and maintain large-scale software systems for solving real-world challenges, is profoundly affected by many revolutionary artificial intelligence tools in general and machine learning in particular. In this roadmap for artificial intelligence in software engineering, we highlight the recent deep impact of artificial intelligence on software engineering by discussing successful stories of applications of artificial intelligence to classic and new software development challenges. We identify the new challenges that the software engineering community has to address in the coming years to successfully apply artificial intelligence in software engineering, and we share our research roadmap toward the effective use of artificial intelligence in the software engineering profession, while still protecting fundamental human values. We spotlight three main areas that challenge the research in software engineering: the use of generative artificial intelligence and large language models for engineering large software systems, the need of large and unbiased datasets and benchmarks for training and evaluating deep learning and large language models for software engineering, and the need of a new code of digital ethics to apply artificial intelligence in software engineering.