Tomás Navarro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tomás Navarro has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alejandro Mozo Quesada
Department of Languages and Computer Sciences, University of Malaga (Andalucia Tech), Malaga, Spain
2 shared publications - Francisco Lopez Valverde
Department of Languages and Computer Sciences, University of Malaga (Andalucia Tech), Malaga, Spain
2 shared publications - Sergio Gálvez
Universidad de Málaga
2 shared publications - Daniel C. Dinis
Instituto de Telecomunicações and Departamento de Electrónica, Telecomunicações e Informática, Universida de Aveiro, Campus Universitário de Santiago, Aveiro, 3810-193, Portugal
1 shared publication Dimitrios Vogiatzis
Department of Information Technology, Cybersecurity and Computer Science, The American College of Greece, Aghia Paraskevi, Greece
1 shared publication- Ioannis T. Christou
American College of Greece, Athens, Greece
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.
- Open Access
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 64-73
Future Trends in AI for Satellite Communications
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 64-73
Open AccessFuture Trends in AI for Satellite Communications