Francisco Lopez Valverde
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Francisco Lopez Valverde has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Sergio Gálvez
Universidad de Málaga
3 shared publications - Alejandro Mozo Quesada
Department of Languages and Computer Sciences, University of Malaga (Andalucia Tech), Malaga, Spain
2 shared publications - Francisco Luna
University of Malaga
2 shared publications - José Manuel Berutich
Departamento de Lenguajes y Ciencias de la Computación, E.T.S. Ingeniería Informática, Málaga, Spain. s:
2 shared publications - Tomás Navarro
European Centre for Space Applications and Telecommunications (ECSAT), European Space Agency, Didcot, U.K.
2 shared publications - Aleksander Zidanšek
Jožef Stefan International Postgraduate School, Jamova cesta 39, SI-1000 Ljubljana, Slovenia
1 shared publication
Latest Publications
- Open Access
- 13 August 2026
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (6) , 3159-3182
Multi-Agent debate system based on large language models: structured deliberation and validation in satellite communications
Structured multi-agent debates among Large Language Models (LLMs) have emerged as a powerful paradigm for enhancing reasoning reliability and argumentative coherence. Motivated by the European Space Agency’s (ESA) interest in trustworthy AI for space operations, this study proposes a moderated, domain-adaptive multi-agent debate framework applied to the high-stakes domain of satellite communications (SatCom). Specifically, it assesses (i) the efficacy of structured deliberation against single-agent baselines, and (ii) the impact of model heterogeneity versus homogeneity. A single-agent baseline is compared against a multi-agent framework deploying a moderator and two domain-specialized experts. These systems utilize local 70B-parameter LLMs in homogeneous (Llama-3.3) and heterogeneous (Llama-3.3 + DeepSeek-R1 + Qwen-2.5) configurations, all augmented with a shared, curated Retrieval-Augmented Generation (RAG) corpus combining academic institutional sources and ESA material from the Nebula portal (SatNex V programme). Outputs from 213 technical queries are evaluated via LLM-as-a-judge across three phases: baseline proficiency, strategic reasoning, and executive readiness. Single-agent systems lead in encyclopedic tasks, where retrieval suffices over deliberation. However, both multi-agent configurations outperform in strategic reasoning, with heterogeneous debates achieving superior performance in executive scenarios by victory margins of up to 2.75 points on a 10-point scale. These results validate architectural diversity as a decisive factor in resolving high-complexity technical conflicts. Ultimately, this work delivers a generalizable, fully traceable deliberation framework suitable for real-world, mission-critical environments. Code, prompts, and evaluation data are publicly available at https://github.com/amozo-es/multi-agent-debate/ .
- 13 August 2026
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (6) , 3159-3182
Open AccessMulti-Agent debate system based on large language models: structured deliberation and validation in satellite communications
Structured multi-agent debates among Large Language Models (LLMs) have emerged as a powerful paradigm for enhancing reasoning reliability and argumentative coherence. Motivated by the European Space Agency’s (ESA) interest in trustworthy AI for space operations, this study proposes a moderated, domain-adaptive multi-agent debate framework applied to the high-stakes domain of satellite communications (SatCom). Specifically, it assesses (i) the efficacy of structured deliberation against single-agent baselines, and (ii) the impact of model heterogeneity versus homogeneity. A single-agent baseline is compared against a multi-agent framework deploying a moderator and two domain-specialized experts. These systems utilize local 70B-parameter LLMs in homogeneous (Llama-3.3) and heterogeneous (Llama-3.3 + DeepSeek-R1 + Qwen-2.5) configurations, all augmented with a shared, curated Retrieval-Augmented Generation (RAG) corpus combining academic institutional sources and ESA material from the Nebula portal (SatNex V programme). Outputs from 213 technical queries are evaluated via LLM-as-a-judge across three phases: baseline proficiency, strategic reasoning, and executive readiness. Single-agent systems lead in encyclopedic tasks, where retrieval suffices over deliberation. However, both multi-agent configurations outperform in strategic reasoning, with heterogeneous debates achieving superior performance in executive scenarios by victory margins of up to 2.75 points on a 10-point scale. These results validate architectural diversity as a decisive factor in resolving high-complexity technical conflicts. Ultimately, this work delivers a generalizable, fully traceable deliberation framework suitable for real-world, mission-critical environments. Code, prompts, and evaluation data are publicly available at https://github.com/amozo-es/multi-agent-debate/ .
- Open Access
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 155675-155696
Adapting LLMs for Satellite Communications: Methodology, Challenges, and Impact
The application of large language models (LLMs) to specialized fields, such as Satellite Communications (SatCom), presents unique challenges due to the extensive and cutting-edge knowledge required. SatCom encompasses a wide range of technical details, protocols, and operational guidelines that must be addressed to produce effective and accurate models for practical use. This paper presents a fine-tuning approach for adapting 7-billion-parameter instructed LLMs (Llama-3v and Mistral) to SatCom, using a proprietary corpus sourced from the European Space Agency (ESA) consisting of domain-specific PDF documents. The confidential nature of this corpus imposes constraints on both model training and evaluation, demanding a sensible text extraction pipeline capable of handling complex structures, such as tables, to preserve critical information. Our fine-tuning methodology employs a carefully configured process, followed by an automatic evaluation framework using a curated Q&A set tailored to SatCom. Models were created in both non-quantified and 8-bit quantized formats, ensuring feasibility for desktop-level inference. The fine-tuned models demonstrated a 6,6% improvement over the baseline LLM, as well as significant gains when compared to retrieval-augmented generation (RAG) methods. These results indicate a promising advancement in the development of LLMs for domain-specific applications within the SatCom field.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 155675-155696
Open AccessAdapting LLMs for Satellite Communications: Methodology, Challenges, and Impact
The application of large language models (LLMs) to specialized fields, such as Satellite Communications (SatCom), presents unique challenges due to the extensive and cutting-edge knowledge required. SatCom encompasses a wide range of technical details, protocols, and operational guidelines that must be addressed to produce effective and accurate models for practical use. This paper presents a fine-tuning approach for adapting 7-billion-parameter instructed LLMs (Llama-3v and Mistral) to SatCom, using a proprietary corpus sourced from the European Space Agency (ESA) consisting of domain-specific PDF documents. The confidential nature of this corpus imposes constraints on both model training and evaluation, demanding a sensible text extraction pipeline capable of handling complex structures, such as tables, to preserve critical information. Our fine-tuning methodology employs a carefully configured process, followed by an automatic evaluation framework using a curated Q&A set tailored to SatCom. Models were created in both non-quantified and 8-bit quantized formats, ensuring feasibility for desktop-level inference. The fine-tuned models demonstrated a 6,6% improvement over the baseline LLM, as well as significant gains when compared to retrieval-augmented generation (RAG) methods. These results indicate a promising advancement in the development of LLMs for domain-specific applications within the SatCom field.
- 1 May 2024
- Published by Szkoła Główna Handlowa GV in e-mentor
- Vol. 104 (2) , 82-90
Transversal skills in applied Artificial Intelligence - the case of the financial sector
Different aspects of modern society can be transformed by the deployment of Artificial Intelligence (AI). AI-powered tools have promoted changes in the financial industry by applying inventive methods for data analysis and automating processes, efficiency enhancement, cost reduction and more personalised services to customers. However, AI algorithms may activate significant ethical and regulatory concerns that should be addressed by the industry and society as a whole. In line with the Erasmus+ project Transversal Skills in Applied Artificial Intelligence - TSAAI (KA220-HED - Cooperation Partnerships in higher education), which aims to establish a training platform, this paper focuses on an analysis of study programmes in formal tertiary education across consortium countries (Spain, Estonia, North Macedonia, Croatia, Germany, and Slovenia) with a special focus on applied artificial intelligence and development of curriculum that will integrate teaching guidelines covering the areas of application of AI technology in the financial and insurance sectors. To this end, a Systematic Review of Literacy (SRL) on the web methodology identifying the existing employability requirements in AI and the Learning-Centred Syllabus (LCS) methodology for curriculum development was applied, with the presented curriculum expected to serve as a framework to develop teaching materials to help students, academics and employees enhance their professional skills, thus satisfying labour market needs.
- 1 May 2024
- Published by Szkoła Główna Handlowa GV in e-mentor
- Vol. 104 (2) , 82-90
Transversal skills in applied Artificial Intelligence - the case of the financial sector
Different aspects of modern society can be transformed by the deployment of Artificial Intelligence (AI). AI-powered tools have promoted changes in the financial industry by applying inventive methods for data analysis and automating processes, efficiency enhancement, cost reduction and more personalised services to customers. However, AI algorithms may activate significant ethical and regulatory concerns that should be addressed by the industry and society as a whole. In line with the Erasmus+ project Transversal Skills in Applied Artificial Intelligence - TSAAI (KA220-HED - Cooperation Partnerships in higher education), which aims to establish a training platform, this paper focuses on an analysis of study programmes in formal tertiary education across consortium countries (Spain, Estonia, North Macedonia, Croatia, Germany, and Slovenia) with a special focus on applied artificial intelligence and development of curriculum that will integrate teaching guidelines covering the areas of application of AI technology in the financial and insurance sectors. To this end, a Systematic Review of Literacy (SRL) on the web methodology identifying the existing employability requirements in AI and the Learning-Centred Syllabus (LCS) methodology for curriculum development was applied, with the presented curriculum expected to serve as a framework to develop teaching materials to help students, academics and employees enhance their professional skills, thus satisfying labour market needs.
- 1 March 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 46, 307-315
Robust technical trading strategies using GP for algorithmic portfolio selection
- 1 March 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 46, 307-315
Robust technical trading strategies using GP for algorithmic portfolio selection
- 1 January 2014
- Published by SAGE Publications in AI Communications
- Vol. 27 (4) , 453-471
On the quest for robust technical trading strategies using multi-objective optimization
We present a robust multi-market optimization methodology for technical trading strategies, whereby robustness is incorporated via the environmental variables of the problem. The search for the optimum parameters is conducted over several markets, in
- 1 January 2014
- Published by SAGE Publications in AI Communications
- Vol. 27 (4) , 453-471
On the quest for robust technical trading strategies using multi-objective optimization
We present a robust multi-market optimization methodology for technical trading strategies, whereby robustness is incorporated via the environmental variables of the problem. The search for the optimum parameters is conducted over several markets, in
- 10 May 2003
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 73 (3) , 233-247
Segmentation of vessels from mammograms using a deformable model
- 10 May 2003
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 73 (3) , 233-247
Segmentation of vessels from mammograms using a deformable model