In the context of software startups, project failure is embraced actively and considered crucial to obtain validated learning that can lead to pivots. A pivot is the strategic change of a business concept, product or the different elements of a business model. A better understanding is needed on different types of pivots and different factors that lead to failures and trigger pivots, for software entrepreneurial teams to make better decisions under chaotic and unpredictable environment. Due to the nascent nature of the topic, the existing research and knowledge on the pivots of software startups are very limited. In this study, we aimed at identifying the major types of pivots that software startups make during their startup processes, and highlighting the factors that fail software projects and trigger pivots. To achieve this, we conducted a case survey study based on the secondary data of the major pivots happened in 49 software startups. 10 pivot types and 14 triggering factors were identified. The findings show that customer need pivot is the most common among all pivot types. Together with customer segment pivot, they are common market related pivots. The major product related pivots are zoom-in and technology pivots. Several new pivot types were identified, including market zoom-in, complete and side project pivots. Our study also demonstrates that negative customer reaction and flawed business model are the most common factors that trigger pivots in software startups. Our study extends the research knowledge on software startup pivot types and pivot triggering factors. Meanwhile it provides practical knowledge to software startups, which they can utilize to guide their effective decisions on pivoting.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
It is essential for startups to quickly experiment business ideas by building tangible prototypes and collecting user feedback on them. As prototyping is an inevitable part of learning for early stage software startups, how fast startups can learn depends on how fast they can prototype. Despite of the importance, there is a lack of research about prototyping in software startups. In this study, we aimed at understanding what are factors influencing different types of prototyping activities. We conducted a multiple case study on twenty European software startups. The results are two folds; firstly we propose a prototype-centric learning model in early stage software startups. Secondly, we identify factors occur as barriers but also facilitators for prototyping in early stage software startups. The factors are grouped into (1) artifacts, (2) team competence, (3) collaboration, (4) customer and (5) process dimensions. To speed up a startup’s progress at the early stage, it is important to incorporate the learning objective into a well-defined collaborative approach of prototyping.
Anh Nguyen-Duc, Xiaofeng Wang, P. Abrahamsson· International Conference on...· 44 citations· ⚡5
Gender issues in software engineering education are gaining research attention due to the desire to promote female participation in the field. The objective of this work is to enhance the understanding of female students' participation in software engineering projects to support gender-aware course optimization. Since 2015, we have investigated the participation of female students in terms of software engineering activities and team dynamics in a software project course that involves a real customer. We found that female students are more active with project management and requirement engineering, while they remain under-represented in highly complex or specific tasks, i.e. architecture work, and user experience design. We found no statistically significant difference in perceived team dynamics between male and female students. Insights on female project activities would facilitate the arrangement of project teams so that learning can be distributed equally across genders
Anh Nguyen-Duc, M. L. Jaccheri, P. Abrahamsson· 2019 IEEE/ACM 41st Internati...· 9 citations
course of 4 AR cycles. During the AR process, the method was used by 44 student startup teams in a practical course setting. Data from the use of the method was collected through self-reporting in the form of modified learning diaries, mentoring meetings with the startup teams, and a qualitative survey. Results: We consider the current version of StartCards useful for early-stage startups based on the data we have collected. The method can also be used as a pedagogical tool in startup education. Conclusions: The paper presents the first published version of the method. While work on the method continues, the method is deemed ready for use.
Kai-Kristian Kemell, Anh Nguyen-Duc, Mari Suoranta et al.· Information and Software Tec...· 25 citations· ⚡1
Reach audiences
Advertise in front of researchers, engineers, and readers.
In this study, we present a solution for the modernization of legacy applications, an area of code generation where LLM-based multi-agent systems are proving essential for complex multi-phased tasks. Legacy applications often contain deprecated components that create compatibility, security, and reliability risks, but high resource costs make companies hesitate to update. We take a step forward to integrate an LLM-based multi-agent system as part of a legacy web application update to provide a cost-effective solution to update legacy applications autonomously. We propose a multi-agent system named a Verifying Agent Pipeline Updater (VAPU), which is designed to update code files in phases while simulating different roles in a software development team. In our previous study, we evaluated the system for legacy version updates by using six legacy web application view files by resulting errors and accomplished requirements. This study extends the previous evaluation of a multi-agent pipeline system by extending the evaluation of VAPU from a single LLM to five LLMs and using the temperature parameter in both 0 to 1 settings. Additionally, we tested the system with 20 open-source Python GitHub projects. The results of the evaluation were compared to Zero-Shot Learning (ZSL) and One-Shot Learning (OSL) prompts. The extended evaluation of VAPU showed that particularly in a low-temperature VAPU can get similar level of error count compared to the ZSL/OSL prompts but with a higher level of fulfilled requirements, depending on the LLM. VAPU showed up to 22.5% increase in the succeeding Python file update requirements compared to ZSL/OSL prompts. The study indicates that an LLM-based multi-agent system is a capable solution to update components of a legacy application autonomously.
Valtteri Ala-Salmi, Z. Rasheed, Malik Abdul Sami et al.· arXiv.org· 3 citations
The use of Large Language Models (LLMs) for autonomous code generation is gaining attention in emerging technologies. As LLM capabilities expand, they offer new possibilities such as code refactoring, security enhancements, and legacy application upgrades. Many outdated web applications pose security and reliability challenges, yet companies continue using them due to the complexity and cost of upgrades. To address this, we propose an LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions. The system distributes tasks across multiple phases, updating all relevant files. To evaluate its effectiveness, we employed Zero-Shot Learning (ZSL) and One-Shot Learning (OSL) prompts, applying identical instructions in both cases. The evaluation involved updating view files and measuring the number and types of errors in the output. For complex tasks, we counted the successfully met requirements. The experiments compared the proposed system with standalone LLM execution, repeated multiple times to account for stochastic behavior. Results indicate that our system maintains context across tasks and agents, improving solution quality over the base model in some cases. This study provides a foundation for future model implementations in legacy code updates. Additionally, findings highlight LLMs' ability to update small outdated files with high precision, even with basic prompts. The source code is publicly available on GitHub: https://github.com/alasalm1/Multi-agent-pipeline.
Valtteri Ala-Salmi, Z. Rasheed, Malik Abdul Sami et al.· International Conference on...· 4 citations
Code-generating tools are increasingly used in software development, yet experience reports on conversational"vibe coding"under production constraints remain limited. This paper presents an experience report from a small full-stack team that applied contextual prompting and explicit architectural constraints to build (i) a multi-project agent learning platform designed for sustained, production-oriented use and (ii) an academic retrieval-augmented generation system. The agent platform supports multiple isolated projects, each with structured memory and background processing, thereby enforcing project-level isolation. The RAG system provides citation-grounded answers, role-based access control, and evaluation tracking. Across both systems, vibe coding accelerated scaffolding and integration. However, the generated code often under-specified isolation rules and infrastructure constraints when these were not explicitly defined. Consequently, aspects such as multi-tenancy, access control, memory policies, and asynchronous processing required deliberate architectural design and verification. We observe a shift in engineering effort from boilerplate implementation toward constraint specification and enforcement auditing. We also identify recurring architectural"non-delegation zones"where conversational code generation remains insufficient for production reliability.
Md Nasir Uddin Shuvo, M. Islam, Mahade Hasan et al.· arXiv.org· 0 citations
Retrieval-Augmented Generation (RAG) systems are emerging as a key approach for grounding Large Language Models (LLMs) in external knowledge, addressing limitations in factual accuracy and contextual relevance. However, there is a lack of empirical studies that report on the development of RAG-based implementations grounded in real-world use cases, evaluated through general user involvement, and accompanied by systematic documentation of lessons learned. This paper presents five domain-specific RAG applications developed for real-world scenarios across governance, cybersecurity, agriculture, industrial research, and medical diagnostics. Each system incorporates multilingual OCR, semantic retrieval via vector embeddings, and domain-adapted LLMs, deployed through local servers or cloud APIs to meet distinct user needs. A web-based evaluation involving a total of 100 participants assessed the systems across six dimensions: (i) Ease of Use, (ii) Relevance, (iii) Transparency, (iv) Responsiveness, (v) Accuracy, and (vi) Likelihood of Recommendation. Based on user feedback and our development experience, we documented twelve key lessons learned, highlighting technical, operational, and ethical challenges affecting the reliability and usability of RAG systems in practice.
M. Hasan, Muhammad Waseem, Kai-Kristian Kemell et al.· EUROMICRO Conference on Soft...· 10 citations· ⚡1
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.
Thomas Debelle, F. Sohrab, Pekka Abrahamsson et al.· Scientific Reports· 1 citation
Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot generate any correct solutions, it receives \textit{zero} learning signal. Providing privileged guidance during training, such as solution prefixes, can help overcome this learning cliff by steering the model towards {correct solutions with non-zero reward}. {We call these rollouts \textit{off-context}: they are generated from a training prompt that contains privileged guidance, while the target objective is defined by the original prompt without that guidance.} {We introduce} Off-Context GRPO (OC-GRPO), a minimally modified variant of GRPO that uses guided rollouts but applies an importance-corrected objective to steer the update back toward the original unguided objective, avoiding the mismatch that destabilizes uncorrected guided training. Empirically, our algorithm achieves a 3.8\% absolute improvement (13.7\% relative gain) over vanilla GRPO on average across standard mathematical reasoning benchmarks with negligible additional cost.
Priyank Agrawal, Ankur Samanta, S. Ghasemlou et al.· 1 citation
Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discover predictive feature transformations from an exponentially large search space. Recent advances in large language models (LLMs) have expanded the expressiveness of AutoFE by enabling feature program generation beyond predefined operator libraries. However, existing LLM-based approaches remain fundamentally limited by stateless generation and homogeneous search: feature proposals are produced from static prompts without accumulating search experience, while single-population exploration quickly converges to dominant transformation patterns and rarely discovers complementary feature compositions across transformation families. We propose TOPOFE, a topology-aware multi-island evolutionary framework for LLM-guided feature engineering. TOPOFE combines family-specialized exploration, adaptive prompt memory, and topology-guided knowledge transfer to efficiently discover diverse and compositional feature programs. Experiments on 29 public tabular datasets demonstrate consistent improvements over state-of-the-art AutoFE methods across classification and regression tasks. Beyond predictive performance, TOPOFE discovers more diverse and transferable feature programs that generalize across multiple downstream predictors and LLM backbones.
The next iteration of Nova is presented, an automated end-to-end JIT compiler that achieves absolute control over hardware mapping by synthesizing fine-grained kernels directly from the computation's structure by extending Nova's compilation pipeline to natively support full Transformer architectures.
Adwaid Suresh, Aparna A Harshini, Jona Delcy et al.· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
