INTIA

International Summer School on LLM-based Agents for Software Engineering

Tue, 16 Sep 2025 00:00:00 +0000

From September 1 to 3, 2025, i3Lab (Quercus Software Engineering Group and INTIA, University of Extremadura) successfully organized the 1st International Summer School on LLM-Based Agents for Software Engineering (LLMA4SE). The event brought together researchers, professionals and students from academia and industry to explore the rapidly evolving field of LLM-based multi-agent systems and their applications in software engineering.

The opening day featured two keynote talks:

AgentWare in Software Engineering: A Taxonomy of LLM-Based Multi-Agent Systems, by Davide Di Ruscio, which sparked stimulating discussions.
Generative AI Models Running in Your Own Infrastructure, delivered by Jesús M. González Barahona, who offered deep insights on openness in AI models.

Participants also enjoyed a hands-on workshop on TDD with the Help of AI, led by Jesús M. González Barahona and Giovanni Rosa. The day concluded with a cultural highlight: a guided tour of the UNESCO World Heritage city of Cáceres.

The second day offered a balanced combination of research and practical applications. The morning began with three particularly interesting presentations:

Multi-agents for Code Generation, by Jie Zhang, addressing current challenges and approaches.
AI and Software Development: An Industry Paradigm Shift, by Mario Corchero Jiménez and David Naranjo, who provided an industry perspective.
From Workflow-based to Fully Agentic Applications: smolagents and LangGraph, by Antonio García Domínguez, who presented various agent development frameworks.

In the afternoon, Antonio García Domínguez guided participants in a highly practical workshop on developing agentic applications with human-in-the-loop using LangGraph. The day also included two enriching social activities: a guided visit to the Helga de Alvear Contemporary Art Museum and a social dinner at the Gran Hotel Don Manuel.

The final day featured particularly inspiring sessions:

Olivier Perard, on AI in Enterprise Architecture.
Marc Alier, with Safe AI in Education – The LAMB Project, focusing on history, ethics and risks.
Merve Astekin, with Software Maintenance with Agentic LLMs, showcasing sustainable AI projects.

The summer school concluded with an advanced workshop, Multi-Agent LLMs and Knowledge Graphs for Monitoring and Sustaining Software Systems, delivered by Adela N. Videsjorden and Simeon Andersen Tverdal.

With the success of this first edition still fresh, we are already working on the next one. We are fully confident that the second edition of our school will be as engaging and enriching as this inaugural event. Our goal is to maintain the high quality of content and the variety of discussions to establish a great meeting point for the community.

Stay tuned for upcoming announcements!

MetrikaBox: An open framework for experimenting with audio classification

Thu, 28 Aug 2025 00:00:00 +0000

We open the (Metrika)Box

Thu, 28 Aug 2025 00:00:00 +0000

After months in the making, instead of keeping the information locked away like in a mystery box, we’ve finally opened it! Our lab is proud to share with you the distilled essence of our work: “MetrikaBox: An open framework for experimenting with audio classification”. The title says it all—no further notes needed.

With this publication, Jorge Perianez-Pascual’s PhD journey reaches a turning point, as it brings together years of research in a single paper. As described there, MetrikaBox’s impact is significant: it has supported the development of many papers and experiments, and it lies at the core of MetrikaMedia, a UEx spin-off company that defines itself as a SaaS solution for multimedia content measurement. And now, it’s available for everyone to explore! What will you do with it? Read the paper, play with the code—and don’t forget to tell us about it!

MetrikaBox is one of the main outcomes of musicgenia, a project funded by Grant CPP2021-008491 from MICIU/AEI/10.13039/50100011033 and by the European Union through NextGenerationEU/PRTR. The goal of musicgenia is to develop a cloud-based platform that provides AI-generated production music as a service for content creators and media, both online (live music generation) and offline (pre-recorded music generation). The platform brings clear benefits: (1) royalty-free music, (2) fully original compositions, (3) an easy way to find music that fits your content, and (4) flexible streaming options, where you pay per second instead of per song.

AI-Based System for Assistance in Minimally Invasive Renal Procedures Using Mixed Reality. First Steps

Tue, 29 Jul 2025 00:00:00 +0000

Everything everywhere... with just one prompt

Mon, 14 Apr 2025 00:00:00 +0000

Following the path set in one of our previous papers, we are pleased to announce the publication of the article “Prompt Once, Segment Everything: Leveraging SAM 2 Potential for Infinite Medical Image Segmentation with a Single Prompt”. The starting question behind these two papers is similar: given the enormous resources needed to develop Artificial Intelligence models specialized in a task, is it feasible to use foundation models for the same tasks without performing costly optimizations on them? To answer this, we focus on a task of vital importance with applications that can save lives: medical image segmentation.

In this article we present a novel approach that leverages SAM 2’s video segmentation capabilities to reduce the number of prompts needed to segment a complete volume of medical images. The study first compares the performance of SAM and SAM 2 in medical image segmentation. Then, our novel approach is presented. The results show that SAM 2 achieves an average improvement of 1.76% in Jaccard Index and 1.49% in Dice Score compared to SAM.

Our next goal is to provide a methodology that allows defining the limit of what we can achieve when using these foundation models.

Surely we’re missing something: after all, we can’t be everywhere at once. 😉 Would you like to share some of your ideas with us? Come see us and let’s talk.

Prompt Once, Segment Everything is one of the outcomes of musicgenia, a project funded by Grant CPP2021-008491 from MICIU/AEI/10.13039/50100011033 and by the European Union through NextGenerationEU/PRTR.

Prompt Once, Segment Everything: Leveraging SAM 2 Potential for Infinite Medical Image Segmentation with a Single Prompt

Mon, 14 Apr 2025 00:00:00 +0000

Beyond Spectrograms: Rethinking Audio Classification from EnCodec's Latent Space

Sun, 16 Feb 2025 00:00:00 +0000

Spectrograms and beyond!

Sun, 16 Feb 2025 00:00:00 +0000

It’s a pleasure to start the year (even though it’s already February) by celebrating the publication of a new paper from our lab. This time, it’s “Beyond Spectrograms: Rethinking Audio Classification from EnCodec’s Latent Space”. In this work, we ask the following question: what if the latent representation of a neural audio codec were used in an audio classification pipeline? What we’ve discovered will surprise you. Take a look at the paper and tell us what you think.

This work is one of the results of the thesis that Jorge Perianez-Pascual, a member of our lab, is working on. Interestingly, the concept of using EnCodec’s latent space for classification was initially described as bordering on unconventional, but our results demonstrate its effectiveness. By going beyond traditional spectrogram-based methods, we discover new possibilities for more efficient and accurate audio classification.

This achievement would not have been possible without the collaboration of Álvaro Rubio Largo and Laura Escobar Encinas, two colleagues from the University of Extremadura who contributed their multidisciplinary expertise both during the development and experimentation process and in writing the paper.

Beyond Spectrograms is one of the outcomes of musicgenia, a project funded by Grant CPP2021-008491 from MICIU/AEI/10.13039/50100011033 and by the European Union through NextGenerationEU/PRTR. The main goal of musicgenia is to develop a cloud-based platform that offers AI-generated music as a service for content creators and media, both online (live music generation) and offline (pre-recorded music generation). The direct benefits of this platform include: (1) royalty-free music, (2) original music, (3) ease of finding suitable music for each content and (4) streaming music, with a flexible consumption model where you pay per second rather than per song.

i3lab at the AI and SE Winter School in Doha, Qatar

Sun, 19 Jan 2025 00:00:00 +0000

From January 19 to 22, two members of i3lab, Pery and Emilio, participated in the Winter School on Artificial Intelligence and Software Engineering organized by the University of Doha for Science and Technology (UDST) in Doha, Qatar.

This event brought together experts, researchers and professionals from around the world to discuss the latest advances in artificial intelligence (AI) and software engineering (SE), two fundamental disciplines for the development of emerging technologies. During four days of conferences, workshops and hands-on sessions, participants explored key areas such as:

✅ Deep learning and generative models, with applications in computer vision, natural language processing and content generation.

✅ AI-driven software development, addressing new methodologies and tools to optimize the creation and maintenance of intelligent systems.

✅ Ethics and regulation in artificial intelligence, a crucial topic in the context of responsible implementation of AI models in society.

✅ AI integration in critical software systems, including applications in healthcare, security and industrial automation.

In addition to academic and technical training, the Winter School allowed i3lab to strengthen its international collaboration network, share experiences with other researchers and explore new ideas for applying Deep Learning in intelligent software development.

The stay in Doha also provided the opportunity to learn more about Qatar’s culture and innovation ecosystem, a country that is strongly betting on artificial intelligence and digital transformation.

We thank UDST for the excellent organization of the event and all speakers and attendees for the enriching discussions. Without a doubt, this experience will bring new perspectives and opportunities for research and development at i3lab.

💡 We keep advancing at the intersection of AI and software engineering! 🚀🔬

If you’d like to know more about our research lines in applying AI to software development, get in touch with us and we’ll tell you about it.

Second Working Seminar of the AI4Software Research Network

Thu, 16 Jan 2025 00:00:00 +0000

On January 16 and 17 we had the great fortune to attend the Second Working Seminar of the AI4Software Research Network organized by our colleagues from Universidad Rey Juan Carlos (URJC), Gregorio Robles and Jesús Gonzalez Barahona.

The seminar was organized mainly around two very interesting round tables and a session of “lightning talks” to learn about the most current work of each node, from evolutionary algorithms behind AutoML proposals to LLM-based agents for requirements engineering. The maturity of the network was evident in the quantity and quality of the work presented.

In our case, Chema delivered the “lightning talk” for the University of Extremadura node, presenting, first, our line of systematic evaluation of LLM-based multi-agent systems for software development and, second, our proposal to organize an AI4Software Summer School in Cáceres, of which we will share more news soon.

Additionally, Roberto had the opportunity to participate in the round table “Where is AI4SE research heading? Expert reflection on trends, emerging areas and approaches that have become obsolete in AI advances in Software Engineering”, which addressed very interesting topics in the current application of LLMs in different software development tasks and also discussed the need for the network to work on how to incorporate the use of LLMs (and agents) into the university Software Engineering degree.

Finally, a demo session was held in which, among other works, we were particularly impressed by the URJC demo of code visualization in augmented reality, using for example the city metaphor as in CodeCity. Below you can see a small web app that allows you to visualize a researcher’s publications with that metaphor using their ORCID. In the example, Tim Berners Lee’s is used.

These have been very intense days of work but also very rewarding. And we return with full energy to continue with our research work in this line.

If you found this interesting, we encourage you to visit the AI4Software Research Network website.

If you’d like to know more about our research lines in applying AI to software development, get in touch with us and we’ll tell you about it.

A multi-criteria decision support system to evaluate the effectiveness of training courses on citizens' employability

Wed, 01 Jan 2025 00:00:00 +0000

Advancing precision in medical image segmentation: A performance analysis of loss functions for COVID-19 lung infection segmentation in computed tomography images

Fri, 01 Nov 2024 00:00:00 +0000

Precision in medical segmentation with composite loss functions

Wed, 25 Sep 2024 00:00:00 +0000

We have a new publication! Our latest paper focuses on analyzing how different loss functions impact the accuracy of medical segmentation with deep learning. Specifically, we evaluated three types (AUFL, DSCL and CE) applied to the detection of COVID-19 lung lesions in CT images, using advanced architectures such as TransUNet, ViT and U-Net.

The results are revealing: the AUFL composite loss function stands out for its accuracy and stability, consistently outperforming the others, especially when segmenting small lesions, such as ground-glass opacities (GGOs), so common in this pathology.

This publication consolidates a research line focused on improving models for precision clinical segmentation, with real applications in AI-assisted diagnosis and treatment scenarios. Our goal: to ensure reliable and reproducible segmentations, even in lower-resolution modalities such as CBCT.

Advancing precision in medical image segmentation: A performance analysis of loss functions for COVID-19 lung infection segmentation in computed tomography images is one of the outcomes of musicgenia, a project funded by Grant CPP2021-008491 from MICIU/AEI/10.13039/50100011033 and by the European Union through NextGenerationEU/PRTR.

Interested in understanding why AUFL achieves better results and how these functions compare across different architectures and imaging modalities? Contact us and we’ll explain it to you.

Analysis of ChatGPT Performance in Computer Engineering Exams

Mon, 25 Mar 2024 00:00:00 +0000

Medical image segmentation with SAM

Fri, 23 Feb 2024 00:00:00 +0000

Great news! Our paper dedicated to analyzing the medical image segmentation capabilities of SAM, Meta’s foundation model, has just been published. In our tests, this model achieves results close to those obtained by models specifically built for this task, and SAM hasn’t been trained to perform segmentation of this specific type of images.

This is our first publication in the field of Medical Image Analysis (MIA). This opens a new research line within the lab, with which we hope to begin fruitful collaboration with various entities in the healthcare field.

Delving into the results obtained… would you like to know why they are so interesting? Get in touch with us and we’ll tell you about it.

No More Training: SAM's Zero-Shot Transfer Capabilities for Cost-Efficient Medical Image Segmentation

Mon, 15 Jan 2024 00:00:00 +0000

Intel supports our research

Mon, 31 Jul 2023 00:00:00 +0000

We already have a brand new Intel GPU in our hands! We requested it a few months ago to use it in the various Artificial Intelligence research projects we are working on. We’ll tell you more after the holidays.

Thanks to Intel for trusting our lab and to Jocelyn for facilitating the entire process. I’m sure this is the first of many collaborations.

Having Intel on board is an honor, but being able to thank John Carmack for sharing the program details via Twitter is a totally unexpected bonus:

Intel is giving away free GPUs for academic work. https://t.co/w5sdEIlkx8
— John Carmack (@ID_AA_Carmack) December 14, 2022

Interested in the topic? Want to know more? Get in touch with us and let’s talk.

JENUI 2023: best paper

Thu, 06 Jul 2023 00:00:00 +0000

On November 30, 2022, OpenAI introduced ChatGPT. Like most people, it caught us by surprise 🤯 with its incredible capabilities. From the very first moment we wondered what impact it would have on the different aspects of our daily lives: in Computer Engineering, in research and in teaching. From an idea proposed by our colleague Roberto, we decided to focus on the latter.

The result of several months of effort is our paper “Impact of ChatGPT on the evaluation methods of a Computer Engineering degree”, which we submitted to JENUI 2023 and for which we were awarded the best paper prize at the conference. In this edition, dominated by ChatGPT (something that has kept some speakers awake at night), the paper “Compete or not: analysis of Wooclap’s competition mode based on performance and audio processing”, by our colleagues from the University of Murcia, was also awarded.

Here you can see Roberto presenting our experience to the rest of the conference attendees (about 10 minutes plus the Q&A session):

As soon as the proceedings are published we will share them so you can read the paper and give us your opinion. In the meantime, here is the abstract:

Generative Artificial Intelligences have experienced significant evolution in recent years and, especially, in 2022. One of the AIs that has caused the most stir in the academic world is ChatGPT, which provides an interface that greatly simplifies the productive use of a large language model. These language models are capable of analyzing and generating texts with great speed and quality. These capabilities could have a relevant impact on teaching-learning methodologies and also on evaluation methods. In order to analyze the possible impact of ChatGPT on evaluation methods, in this work, ChatGPT’s ability to solve exams from 15 Software Engineering courses in a Computer Engineering degree has been tested. The results show that ChatGPT could have a clear impact on evaluation methods; as it is capable of passing a significant number of questions and problems of different nature in multiple courses. As a main contribution, a detailed study of the results by question and problem typology is provided, which allows establishing recommendations to be taken into account in the design of evaluation methods.

Interested in the topic? Want to collaborate? Get in touch with us and let’s talk.

Update: You can read the cited paper right here.

Impact of ChatGPT on the evaluation methods of a Computer Engineering degree

Wed, 05 Jul 2023 00:00:00 +0000

ADAPIMMA

Tue, 04 Jul 2023 11:31:59 +0200

Copyright management in Spain has always been a hot-button issue that has sparked great controversy. Special mention deserves the management of copyright for musical pieces. To manage these rights there is SGAE (General Society of Authors and Publishers) which maintains a certain monopoly. Copyright management is governed by the Intellectual Property Law, which in its 1996 version is somewhat vague regarding distribution criteria. So vague is the wording that it is not clear how SGAE charges broadcasting entities, such as radio stations. In some cases it is done based on the billing volume of the broadcasting entity, applying a percentage. That is, it is independent of the music used by the station and, being so, there is no way to make a fair distribution among the authors who provide that music. In other cases, estimates of music usage are made and based on that the management company bills. This can produce situations where young talented authors with short and less established careers are not receiving adequate compensation for their work and may be discouraged from continuing their career in this field.

Precisely the objective of this project is to investigate the techniques that would allow developing a system capable of i) discriminating the use made of music in radio media according to its classification in the new Intellectual Property Law (solution to the first problem) and ii) associating the exact use made of the musical piece to its original author in order to make an equitable distribution of copyright royalties (solution to the second problem). The development of this proposal would represent a significant innovation in the music world that could be an important source, not only of potential clients worldwide, but also of international investments that allow the internationalization of the Extremadura ICT model, both fundamental lines of the Employment, Entrepreneurship and Innovation axis of the Regional Green and Circular Economy Strategy, Extremadura 2030. Notably, due to its evolution and potential trajectory in Extremadura, the ICT sector is an active hub of transversal technology production and a driver of the establishment of software development companies, which can be considered green companies as they do not generate waste.

Results

The article “A Hybrid Multidimensional Recommender System for Radio Programs”, published in the journal “Expert Systems with Applications” by Elsevier, is a direct result of this project.

Its source code is available through two GitHub projects:

A demo is also available.

SAM for medical image segmentation

Tue, 23 May 2023 15:00:53 +0200

The source code for this project is located in this repository.

MusicGenia

Fri, 12 May 2023 13:17:36 +0200

MusicGenia’s main goal consists in building a cloud-based platform to offer AI-generated production music as a service for content creators and media, which can be consumed online (live music generation) or offline (recorded music generation). The direct benefits of that platform are: (1) music free of royalties; (2) original music; (3) easy to find music suiting your content; and (4) music on stream (consume as much as you need, pay per seconds not per song).

Guest lecture by alumnus Mario Corchero

Tue, 29 Nov 2022 17:30:00 +0000

Roberto Rodríguez Echeverría and José María Conejero Manzano have organized a guest lecture by UEx alumnus Mario Corchero for current students. Mario currently works at Bloomberg and in his talk he wants to show our students how the courses he took in the degree program have been useful for solving real-world problems and challenges he has encountered in his work at Bloomberg. He will be joined by Javier Zugasti to tell you about the job opportunities Bloomberg offers.

The talk will take place on Tuesday, November 29, at 5:30 PM in the Auditorium of the Polytechnic School.

Although initially aimed at 3rd and 4th year students, it can be beneficial for any student, regardless of their year.

Mario Corchero is a Senior Software Developer at Bloomberg. He leads the Python infrastructure team, enabling the company to work effectively in Python, building company-wide libraries and tools. His professional experience resides mainly in Python and C++, and he has contributed some patches to multiple Python open source projects.

Javier Zugasti holds a degree in Senior Telecommunications Engineering from the Polytechnic University of Madrid. After two years working in Germany in the automotive sector, Javier has spent 12 years working at Bloomberg Engineering as a software developer and managing engineering teams producing financial applications for the Bloomberg Terminal. The last 3 of those years managing the News Production Engineering department that supports the nearly 4000 journalists around the world responsible for creating Bloomberg News content.

Update: the event was a resounding success!

If you are interested in their internships or job positions, you can find more information here:

Homeria at the first Cáceres Talk 2022

Thu, 24 Nov 2022 18:30:00 +0000

On November 24, at 6:30 PM, as part of the first Cáceres Talk event, Fernando Sánchez Figueroa and Juan Carlos Preciado will tell the success story of WinDelivery, created by Homeria and now part of Glovo. This is a highly recommended talk whether you’re interested in learning more about the process of transferring knowledge from university to business, or if you’re curious to know how an Extremadura spin-off can compete with multinational companies. Additionally, Fernando and Juan Carlos, co-founders of Homeria, will share all the setbacks they’ve faced along the way, what they learned from them, and how this learning has led them to where they are today.

If you wish to attend, reserve your spot before capacity is reached.

Update: the event in Región Digital.

Metrikamedia at Foro Conecta Empresas 2022

Thu, 24 Nov 2022 09:30:00 +0000

On Thursday, November 24, 2022, as part of the technology showroom Foro Conecta Empresas, Metrikamedia, a spin-off of the UEx, presents one of the technologies developed by their company, which is used to separate voice and music within radio broadcasts in order to facilitate auditing by advertisers and control companies. As a demonstration of the platform’s usefulness, visitors who wish to do so can try to identify a piece of music playing in the background while a speaker talks.

Attendance at the event is free and no reservation is required. Don’t miss the opportunity to chat with those responsible for applying Artificial Intelligence techniques in real projects.

National project awarded

Thu, 13 Oct 2022 00:00:00 +0000

National project from the 2021 Knowledge Generation Call awarded for the development of Reproducible and Replicable Data Science Processes.

Last October we received the news that the Ministry of Science and Innovation had approved our project proposal titled “Model-Driven Engineering for Data Science Projects”, led by José M. Conejero. Thanks to this, we will be able to investigate new techniques to improve the reproducibility and replicability of data science projects by applying concepts related to Model-Driven Software Development. Furthermore, by applying these techniques, some of the current challenges of this type of projects can be addressed, such as fairness or data provenance. With all this, this project will help address the problem known as the reproducibility crisis, which began to emerge in disciplines related to medicine and psychology.

You can find more information about the awarding of projects from this call in the final resolution proposal of the 2021 grant awarding procedure for “KNOWLEDGE GENERATION PROJECTS” within the State Program to Promote Scientific-Technical Research and its Transfer, from the State Plan for Scientific, Technical and Innovation Research 2021-2023.

Music generation through deep learning

Mon, 03 Oct 2022 00:00:00 +0000

On November 3 and 4, as part of the Computer Science Doctoral Program at the University of Almería, Roberto Rodríguez Echeverría, University of Extremadura, delivered the course Content and/or recognizable pattern generation through neural networks, with the participation of Jorge Periánez Pascual, MetrikaMedia.

“It has been a while since relying on artificial intelligence to help us in our daily work stopped being a dream and became a reality. On a daily basis we use machine learning models to suggest the next words we type on our phones, to give just one example. What we never would have imagined is that these artificial intelligences would help us create creative content such as code for our programs, images following textual descriptions or, as we explain in this seminar, music,” commented UEx Associate Professor Roberto Rodríguez Echeverría.

The seminar content was as follows:

Introduction to deep learning
Recurrent Networks and Transformers
Content Generation
Image Generation with Variational Autoencoders
Music generation with LSTM and Transformers

This and other seminars are the result of collaboration between industry and University. From i3lab, one of the working groups of Quercus Software Engineering Group, we are committed to training new engineers in subjects such as artificial intelligence and everything related to it, such as MLOps. Interested? Get in touch with us and let’s talk.

A Model-Driven Approach for Systematic Reproducibility and Replicability of Data Science Projects

Tue, 28 Jun 2022 00:00:00 +0000

CompareML: A Novel Approach to Supporting Preliminary Data Analysis Decision Making

Wed, 01 Jun 2022 00:00:00 +0000

Suggesting model transformation repairs for rule-based languages using a contract-based testing approach

Tue, 01 Feb 2022 00:00:00 +0000

A model-driven approach for the definition of reproducible and replicable data analysis projects

Sat, 01 Jan 2022 00:00:00 +0000

SimulateIoT: Domain Specific Language to Design, Code Generation and Execute IoT Simulation Environments

Fri, 25 Jun 2021 00:00:00 +0000

Applying data driven decision making to rank vocational and educational training programs with TOPSIS

Mon, 01 Mar 2021 00:00:00 +0000

A Hybrid Multidimensional Recommender System for Radio Programs

Sat, 20 Feb 2021 00:00:00 +0000

A Real-Life Machine Learning Experience for Predicting University Dropout at Different Stages Using Academic Data