AI-Powered Code Generation Evaluating the Effectiveness of Large Language Models (LLMs) in Automated Software Development

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.

With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of RL in code optimization and generation, highlighting its role in enhancing compiler optimization, resource allocation, and the development of frameworks and tools. Subsequent sections first delve into the intricate processes of compiler optimization, where RL algorithms are leveraged to improve efficiency and resource utilization. The discussion then progresses to the function of RL in resource allocation, emphasizing register allocation and system optimization. We also explore the burgeoning role of frameworks and tools in code generation, examining how RL can be integrated to bolster their capabilities. This survey aims to serve as a comprehensive resource for researchers and practitioners interested in harnessing the power of RL to advance code generation and optimization techniques.

Automated code generation has revolutionized software development, enabling developers to accelerate project timelines and reduce manual coding errors significantly. As reliance on these technologies grows, the inherent weaknesses of generated code become increasingly apparent. Recent studies have shown that code produced by AI is not inherently safer or of higher quality than human-written code, often replicating existing vulnerabilities. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">To this end, we propose SECURECODER, which integrates Retrieval-Augmented Generation (RAG) with Common Weakness Enumeration (CWE). SECURECODER first utilizes the advanced reasoning capabilities of large language models (LLMs) to generate natural language descriptions of the code’s core business logic and functionality. Then, from a semantic perspective, it matches the requirements of the code generation task with the CWE descriptions through a multi-label classification process. Finally, based on the matched CWE, SECURECODER generates a list of security guidelines the code generation model must adhere to. Breaking down end-to-end code generation tasks into single-target tasks that LLMs excel at ensures that the generated code not only meets functional requirements but also adheres to best security practices, thereby enhancing the interpretability of the automated code generation process. After evaluating 2 programming languages and 7 LLMs on Coploit-generated code, SECURECODER has great generalization capability and could be applied to more programming languages and vulnerability types. SECURECODER could significantly decrease the security weakness in the AI-generated code and is able to mitigate more than 65% of vulnerabilities exposed to software developers. Compared to the baseline open-source LLMs, code vulnerabilities were reduced by at least 14% and the code business logic was not affected.

The paper studies the problem of software code migration during the transition from the old version of the SAP ERP 6.0 system to modern ERP platforms, in particular SAP S/4HANA. The necessity of automation of the migration process using artificial intelligence methods and tools is substantiated. A comprehensive analysis of existing academic and industrial case studies confirmed the feasibility of using large language models for code migration. A number of advantages of the approach based on large language models are revealed, in particular, the ability to handle various migration scenarios. The key risks and limitations common in the enterprise environment are highlighted, including data security, privacy, high cost of API calls and limited knowledge of models regarding the subject area. A method is developed for selecting a large open source language model that can be safely used in the enterprise landscape, thereby mitigating the risks associated with cloud solutions. The method is based on the developed system of criteria, including: model size, context window size, license type, support for fine-tuning training, focus on code quality (measured using a reference dataset), support for model quantization and community support. The hybrid AHP-TOPSIS method is proposed for systematic ranking of candidate models. The AHP method was used to check the weights of the criteria, while TOPSIS was used to rank the models based on their proximity to the ideal solution. Based on the developed method, three large language models were selected: Qwen 2.5 Coder 14B, DeepSeek-Coder-V2 16B and Llama 3.1 8B. A comprehensive testing plan for the selected models was developed for further experimental studies. The scientific novelty of the work lies in the development of a method for selecting large language models for custom code migration tasks, which differs from the existing system of model selection criteria and the use of a hybrid AHP-TOPSIS approach for ranking candidate models. The practical value of the work is that the developed method allows you to select a model taking into account the constraints of the corporate environment and information security requirements, which will increase the level of automation in the migration of AVAP when switching to new versions of ERP systems from SAP SE. The developed method can be applied to the selection of large language models when upgrading any large computer systems developed in both open source and proprietary programming languages.

In today’s rapidly evolving business landscape, Artificial Intelligence (AI), and specifically Large Language Models (LLMs), are redefining how organizations operate, make decisions, and engage with customers. AI-driven technologies have become indispensable, providing businesses with powerful tools to streamline operations, derive actionable insights from vast data, and foster more meaningful customer interactions. For business leaders, scholars, and practitioners alike, understanding the transformative potential of AI isn’t just advantageous—it’s essential to staying competitive in an increasingly data-driven world.This editorial delves into recent scholarly advancements in LLM applications within business contexts, analyzing studies that explore AI’s potential across various domains, from decision support to creative industries. By introducing a structured framework, this editorial highlights key insights and contributions from recent studies, assessing their value to academia and industry. The following comparative analysis sheds light on how these innovations shape our understanding of AI’s role in business while pointing to future research directions.Puyt and Madsen's (2024) study stands out as a foundational exploration of LLM accuracy, assessing ChatGPT-4's ability to recount the history of the SWOT analysis-a vital business strategy tool. Their findings reveal that, while ChatGPT-4 effectively conveys general concepts, it struggles with detailed historical information, often producing inaccuracies or "hallucinations." This gap underscores the need for LLMs to be trained with verified academic data, particularly for strategic business applications that demand precision. This study not only contributes to the literature by proposing methods to evaluate AI accuracy in historical contexts but also highlights the importance of rigorous information vetting in industry settings where reliability is crucial.In contrast, Raikov et al. (2024) explore a hybrid intelligence model that combines LLM capabilities with explainable AI (XAI) principles to enhance human-machine collaboration. Their approach emphasizes cognitive semantics, improving transparency and decision-making efficiency. The hybrid model's real-time adaptability addresses the needs of complex, regulated industries such as finance and healthcare, where trust in AI decisions is paramount. Academically, this study provides a valuable addition to XAI literature by demonstrating how LLMs can bridge the gap between AI autonomy and human oversight, making it a model for future human-AI interactions in complex business environments.Another significant study by Mariotti and colleagues (2024) examines the integration of LLMs with enterprise knowledge graphs to enhance data-driven decision-making. By enabling organizations to leverage knowledge graphs for more accurate and scalable data retrieval, this research provides a robust framework for businesses seeking efficient knowledge management systems. The academic contribution here lies in advancing the dialogue between LLMs and knowledge graphs, emphasizing ethical data handling and quality standards essential for industry applications. For enterprises, the study offers practical solutions to achieve streamlined data management, balancing automation with privacy and security. 2024) take a different approach, investigating LLMs' role in creative industries, specifically within fashion design. They introduce a hybrid intelligence model that supports creative processes, allowing AI to complement rather than replace human ingenuity. While LLMs in this field demonstrate potential in automating repetitive design tasks and enhancing customer personalization, the study reveals limitations in AI's ability to handle spatial and stylistic nuances. This study's academic contribution lies in promoting human-AI co-creation, inspiring further research into AI applications across diverse creative sectors, including media and marketing.Collectively, these studies not only illuminate LLMs' transformative potential in business but also highlight critical ethical and operational considerations. Ensuring accuracy, transparency, and data privacy are vital to responsibly integrating AI into business workflows. Future research should focus on enhancing LLM accuracy, refining hybrid intelligence models, and exploring creative AI applications, all while maintaining ethical standards. As LLMs evolve, interdisciplinary collaborations will be essential to harness their full potential, making AI an ethical, effective, and innovative force in the business world.

Large Language Models (LLMs) excel in code-related tasks like code generation, but benchmark evaluations often overlook task characteristics, such as difficulty. Moreover, benchmarks are usually built using tasks described with a single prompt, despite the formulation of prompts having a profound impact on the outcome. This paper introduces a generalist approach, TaskEval, a framework using diverse prompts and Item Response Theory (IRT) to efficiently assess LLMs’ capabilities and benchmark task characteristics, improving the understanding of their performance. Using two code generation benchmarks, HumanEval + and ClassEval , as well as 8 code generation LLMs, we show that TaskEval is capable of characterising the properties of tasks. Using topic analysis, we identify and analyse the tasks of 17 and 21 topics within the benchmarks. We also cross-analyse tasks’ characteristics with programming constructs (e.g., variable assignment, conditions, etc.) used by LLMs, emphasising some patterns with tasks’ difficulty. Finally, we conduct a comparison between the difficulty assessment of tasks by human annotators and LLMs. Orthogonal to current benchmarking evaluation efforts, TaskEval can assist researchers and practitioners in fostering better assessments of LLMs. The tasks’ characteristics can be used to identify shortcomings within existing benchmarks or improve the evaluation of LLMs.

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

Code generation has largely improved development efficiency in the era of large language models (LLMs). With the ability to follow instructions, current LLMs can be prompted to generate code solutions given detailed descriptions in natural language. Many research efforts are being devoted to improving the correctness of LLM-generated code, and many benchmarks are proposed to evaluate the correctness comprehensively. Despite the focus on correctness, the time efficiency of LLM-generated code solutions is under-explored. Current correctness benchmarks are not suitable for time efficiency evaluation since their test cases cannot well distinguish the time efficiency of different code solutions. Besides, the current execution time measurement is not stable and comprehensive, threatening the validity of the time efficiency evaluation. To address the challenges in the time efficiency evaluation of code generation, we propose COFFE, a code generation benchmark for evaluating the time efficiency of LLM-generated code solutions. COFFE contains 398 and 358 problems for function-level and file-level code generation, respectively. To improve the distinguishability, we design a novel stressful test case generation approach with contracts and two new formats of test cases to improve the accuracy of generation. For the time evaluation metric, we propose efficienct@k based on CPU instruction count to ensure a stable and solid comparison between different solutions. We evaluate 14 popular LLMs on COFFE and identify four findings. Based on the findings, we draw some implications for LLM researchers and software practitioners to facilitate future research and usage of LLMs in code generation.

ABSTRACTCode generation for users' intent has become increasingly prevalent with the large language models (LLMs). To automatically evaluate the effectiveness of these models, multiple execution‐based benchmarks are proposed, including specially crafted tasks, accompanied by some test cases and a ground truth solution. LLMs are regarded as well‐performed in code generation tasks if they can pass the test cases corresponding to most tasks in these benchmarks. However, it is unknown whether the test cases have sufficient test adequacy and whether the test adequacy can affect the evaluation. In this paper, we conducted an empirical study to evaluate the test adequacy of the execution‐based benchmarks and to explore their effects during evaluation for LLMs. Based on the evaluation of the widely used benchmarks, HumanEval, MBPP, and two enhanced benchmarks HumanEval+ and MBPP+, we obtained the following results: (1) All the evaluated benchmarks have high statement coverage (above 99.16%), low branch coverage (74.39%) and low mutation score (87.69%). Especially for the tasks with higher cyclomatic complexities in the HumanEval and MBPP, the mutation score of test cases is lower. (2) No significant correlation exists between test adequacy (statement coverage, branch coverage and mutation score) of benchmarks and evaluating results on LLMs at the individual task level. (3) There is a significant positive correlation between mutation score‐based evaluation and another execution‐based evaluation metric () on LLMs at the individual task level. (4) The existing test case augmentation techniques have limited improvement in the coverage of test cases in the benchmark, while significantly improving the mutation score by approximately 34.60% and also can bring a more rigorous evaluation to LLMs on code generation. (5) The LLM‐based test case generation technique (EvalPlus) performs better than the traditional search‐based technique (Pynguin) in improving the benchmarks' test quality and evaluation ability of code generation.

<title>Abstract</title> Automated code generation has advanced significantly with large language models (LLMs), yet their performance in emerging domain-specific languages for practical software development remains largely untested. This gap is particularly critical for major, rapidly growing platforms like Huawei's HarmonyOS. Powering over 900 million devices, the HarmonyOS ecosystem is shifting to a native-only application environment with the HarmonyOS NEXT update. This shift makes development in its native ArkTS UI language essential, driving an urgent need for effective developer tools. Addressing this industry challenge, we conduct the first systematic evaluation of Large Language Models (LLMs) on their ability to generate valid ArkTS code to accelerate the software development lifecycle and assist developers in mastering this new language. To ground our evaluation in practical scenarios, we introduce two curated datasets: a test dataset, \textit{ArkTS-Test}, and a training dataset for fine-tuning, both derived from common UI development tasks in ArkTS. Using these datasets, we evaluate a diverse range of LLMs—from large-scale proprietary models (e.g., Claude, Gemini, DeepSeek-V3, Qwen3 Coder, from 70b to up to 671B total parameters) to smaller open-source models (7B–14B) and report our observations. Next, we propose a methodology called Iterative Compilation Feedback (ICF), which enables LLMs to autonomously correct their own code by leveraging compiler error messages. Our experiments show that ICF boosts the syntactic accuracy of large-scale LLMs to as high as 91\%. Furthermore, we show that fine-tuning a small-scale LLM (GPT-4o-mini) and combining it with our ICF method yields results comparable to the best-performing large-scale models. Finally, we conclude with a detailed categorization of compilation errors, identifying which types our ICF method resolves most effectively and which persist due to model knowledge limitations.

As generative Artificial Intelligence (AI) models become increasingly integrated into software development workflows, understanding their efficiency and code quality is critical. This study offers a comprehensive comparison of three leading AI models—ChatGPT GPT-4-turbo, Claude Sonnet, and DeepSeek-V3—for automated code generation, focusing specifically on sorting algorithms. The models are evaluated across multiple metrics including execution time, memory usage, peak memory consumption, logical and physical file sizes, and code readability. Python implementations of Insertion Sort, Merge Sort, Quick Sort, and Heap Sort are generated by each model and benchmarked in a consistent Linux Docker environment. Results reveal that ChatGPT leads in overall efficiency, with the fastest average execution time, the lowest peak memory usage, and the highest readability scores. DeepSeek demonstrated competitive performance, especially in producing readable code, while Claude showed higher memory consumption and lower readability. This analysis provides practical insight into the trade-offs between code quality and system performance in AI-generated programming, offering valuable guidance for researchers and developers alike.

In the context of the rapid development of Large Language Models (LLMs), the field of software development has undergone significant transformations presenting both opportunities and challenges for software development professional cultivation. This study systematically analyzes the applications of LLMs in software development and their impact on this cultivation, exploring the opportunities and challenges in enhancing programming efficiency, promoting personalized learning, improving interdisciplinary skills, and addressing over-reliance on LLMs and related tools. Through literature analysis, this study reviews the impact of LLMs on programming efficiency, code quality, and project management and evaluates the requirements and directions for professional cultivation in response to these changes. The research results indicate that while LLMs bring numerous opportunities, they also pose challenges such as rapid technological updates and a tendency toward over-reliance on tools. Therefore, this study proposes a series of optimized professional cultivation strategies to adapt to the technological developments and industry demands of the new era, thereby enhancing the capability of higher education institutions to cultivate software professionals who meet future needs.

Recently, Large Language Models (LLMs) have showcased their potential in various natural language processing tasks, including code generation. However, while significant progress has been made in adapting LLMs to generate code for several imperative programming languages and tasks, there remains a notable gap in their application to declarative formalisms, such as Answer Set Programming (ASP). In this paper, we move a step towards exploring the capabilities of LLMs for ASP code generation. First, we perform a systematic evaluation of several state-of-the-art LLMs. Despite their power in terms of number of parameters, training data and computational resources, empirical results demonstrate inadequate performances in generating correct ASP programs. Therefore, we propose LLASP, a fine-tuned lightweight model specifically trained to encode fundamental ASP program patterns. To this aim, we create an ad-hoc dataset covering a wide variety of fundamental problem specifications that can be encoded in ASP. Our experiments demonstrate that the quality of ASP programs generated by LLASP is remarkable. This holds true not only when compared to the non-fine-tuned counterpart but also when compared to the majority of eager LLM candidates, particularly from a semantic perspective. All the code and data used to perform the experiments are publicly available: https://github.com/EricaCoppolillo/LLASP.

BackgroundThe exponential growth of medical knowledge presents a paradox for modern medical education. While access to information is immediate, applying it in a clinically meaningful way remains a challenge. Large language models (LLMs), such as ChatGPT, are widely used for information retrieval, yet their role in dynamic, high-pressure clinical learning remains poorly understood.ObjectiveThis study aims to evaluate whether unstructured access to an LLM improves decision-making, teamwork, and confidence in trauma education for medical students.MethodsThis randomized controlled pilot study involved 41 final-year medical students participating in a trauma simulation session. Students self-selected into teams of 4 to 6 and were randomized to either an LLM-assisted group (ChatGPT-4o mini) or a control group without LLM access. All teams completed 18 video-based trauma scenarios requiring time-sensitive clinical decisions. Prompting was unrestricted. Confidence and trauma exposure were assessed using pre- or postquestionnaires. Facilitators rated teamwork (1-5), decision accuracy, and response times. Knowledge retention was measured 4 weeks later via an online quiz.ResultsConfidence in trauma management improved in both groups (P<.001), with larger gains in the non-LLM group (P=.02). LLM support did not enhance the decision accuracy or speed and was associated with longer response times in some complex cases. Teams without LLMs demonstrated more active discussion and scored higher in teamwork ratings (median 5.0 [IQR 5.0-5.0] vs median 3.5 [IQR 3.0-4.5]; P=.08). Students primarily used the LLM for fact-checking but reported vague or overly general responses. Knowledge retention was high across both groups and did not differ significantly (P=.33).ConclusionsWhile students appreciated the inclusion of artificial intelligence (AI), unstructured LLM use did not improve performance and may have disrupted the group reasoning. The use of non-English prompting likely contributed to lower AI performance, underscoring the importance of language alignment in LLM applications. This pilot study highlights the need for structured AI integration and targeted instruction in AI literacy. Simulation-based trauma education proved effective and well received, but optimizing the educational value of LLMs will require thoughtful curricular design. Further studies with more students are needed to define best practices for LLM use in clinical education.

With the rapid evolution of artificial intelligence (AI), its potential implications for higher education have become a focal point of interest. This study delves into the capabilities of AI in physics education and offers actionable AI policy recommendations. Using openAI’s flagship gpt-3.5-turbo large language model (LLM), we assessed its ability to answer 1337 physics exam questions spanning general certificate of secondary education (GCSE), A-Level, and introductory university curricula. We employed various AI prompting techniques: Zero Shot, in context learning, and confirmatory checking, which merges chain of thought reasoning with reflection. The proficiency of gpt-3.5-turbo varied across academic levels: it scored an average of 83.4% on GCSE, 63.8% on A-Level, and 37.4% on university-level questions, with an overall average of 59.9% using the most effective prompting technique. In a separate test, the LLM’s accuracy on 5000 mathematical operations was found to be 45.2%. When evaluated as a marking tool, the LLM’s concordance with human markers averaged at 50.8%, with notable inaccuracies in marking straightforward questions, like multiple-choice. Given these results, our recommendations underscore caution: while current LLMs can consistently perform well on physics questions at earlier educational stages, their efficacy diminishes with advanced content and complex calculations. LLM outputs often showcase novel methods not in the syllabus, excessive verbosity, and miscalculations in basic arithmetic. This suggests that at university, there’s no substantial threat from LLMs for non-invigilated physics questions. However, given the LLMs’ considerable proficiency in writing physics essays and coding abilities, non-invigilated examinations of these skills in physics are highly vulnerable to automated completion by LLMs. This vulnerability also extends to pysics questions pitched at lower academic levels. It is thus recommended that educators be transparent about LLM capabilities with their students, while emphasizing caution against overreliance on their output due to its tendency to sound plausible but be incorrect.