arXiv subjects

Jorge Valverde-Rebaza

Publications and source records attributed to Jorge Valverde-Rebaza.

3 recordsLinked to original sources

arXiv2026

Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management

Generative AI is increasingly being used informally in Air Traffic Management (ATM) for tasks such as flight plan generation, trajectory interpretation, and constraint checking. Although these tools can reduce workload and accelerate planning, their non-deterministic outputs create safety and operational risks in human-in-the-loop settings. This paper proposes the AI Trust and Assurance Layer (ATAL), a model-agnostic decision assurance architecture that evaluates whether AI-generated flight-planning outputs are sufficiently reliable for operational use. ATAL combines semantic stability under prompt variation, operational consistency of structured outputs, and normative constraint validation against domain rules, and maps these signals to a Decision Readiness Level (DRL) for human operators. An ATM-inspired experimental study shows how unsafe, inconsistent, or misleading outputs can be identified before influencing flight-plan validation or execution. Although demonstrated in aviation, the framework is also transferable to other safety-critical decision-support domains that require human oversight under regulatory constraints.

cs.AI↗

arXiv2025

GenIA-E2ETest: A Generative AI-Based Approach for End-to-End Test Automation

Software testing is essential to ensure system quality, but it remains time-consuming and error-prone when performed manually. Although recent advances in Large Language Models (LLMs) have enabled automated test generation, most existing solutions focus on unit testing and do not address the challenges of end-to-end (E2E) testing, which validates complete application workflows from user input to final system response. This paper introduces GenIA-E2ETest, which leverages generative AI to generate executable E2E test scripts from natural language descriptions automatically. We evaluated the approach on two web applications, assessing completeness, correctness, adaptation effort, and robustness. Results were encouraging: the scripts achieved an average of 77% for both element metrics, 82% for precision of execution, 85% for execution recall, required minimal manual adjustments (average manual modification rate of 10%), and showed consistent performance in typical web scenarios. Although some sensitivity to context-dependent navigation and dynamic content was observed, the findings suggest that GenIA-E2ETest is a practical and effective solution to accelerate E2E test automation from natural language, reducing manual effort and broadening access to automated testing.

cs.SE↗

arXiv2025

Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting

Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the Multi-Layered Self-Reflection with Auto-Prompting (MAPS) framework, a novel approach designed to enhance multi-step mathematical reasoning in LLMs by integrating techniques such as Chain of Thought (CoT), Self-Reflection, and Auto-Prompting. Unlike traditional static prompting methods, MAPS employs an iterative refinement process. Initially, the model generates a solution using CoT prompting. When errors are detected, an adaptive self-reflection mechanism identifies and analyzes them, generating tailored prompts to guide corrections. These dynamically adjusted prompts enable the model to iteratively refine its reasoning. Experiments on four well-established benchmarks across multiple LLMs show that MAPS significantly outperforms standard CoT and achieves competitive results with reasoning-optimized models. In addition, MAPS enables general-purpose LLMs to reach performance levels comparable to specialized reasoning models. While deeper reflection layers improve accuracy, they also increase token usage and costs. To balance this trade-off, MAPS strategically limits reflection depth, ensuring an optimal balance between cost and reasoning performance.

cs.CL↗