Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 74 for “"agentic AI"”.
-
Self-Improving LLM Contexts for Agentic AI
… thesis investigates context adaptation for domain-specific LLM agents in a threat intelligence environment. In collaboration with Recorded Future, we implement and evaluate a framework based on Agentic Context Engineering (ACE) for optimizing a search-oriented LLM agent through iterative …
-
Student Perceptions of Agentic AI in Computer Science Education
Agentic artificial intelligence and large language models (LLMs) such as ChatGPT and similar AI systems have quickly become common tools in computer science education. Students are now using these systems for a range of tasks, such as explaining concepts, debugging code, generating examples, and …
-
Foundation Models for Long-Range Person Recognition and Agentic AI
… models that extend person recognition and agentic AI along three connected lines: body-centric foundation models for long-range recognition (Part~I), transfer of those foundations across biometric modalities (Part~II), and agentic AI for procedure understanding and content generation …
-
Implementation of a Local LLM Serving System for Agentic AI
This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding …
-
Agentic AI Framework for Web Vulnerability Detection, Mitigation and Patching
… candidate findings rather than reviewable repairs. Static and dynamic analysis tools can identify possible weaknesses at scale, but the path from a finding to a validated, scoped, and review ready patch remains weakly automated and difficult to inspect. This thesis investigates whether a …
-
Multimodal and Agentic AI for Cognitive Accessibility and Linguistic Preservation
Artificial Intelligence (AI) has become a transformative tool in enhancing cognitive accessibility and preserving linguistic heritage. This thesis investigates the convergence of Generative AI (Gen AI), multimodal learning, and agentic AI to address challenges such as language learning and …
-
Towards agentic AI for point-of-care echocardiography reasoning and interpretation
Cardiovascular disease remains the leading cause of death worldwide, and point-of-care ultrasound (POCUS) has expanded cardiac assessment beyond the specialist echocardiography laboratory. However, interpreting a focused bedside examination requires more than visual recognition. Clinicians must …
-
AgenticRCA: An Industry-Driven Agentic AI Framework for Incident Root Cause Analysis
… cause analysis (RCA) of production incidents remains a significant challenge in telecommunication, requiring engineers to synthesize information from incident descriptions, observability data, and documentation while under time pressure. We present AgenticRCA, a multi-agent framework for …
-
Design of agentic ai systems for automated data extraction in medical processes /
… thesis examines the design and evaluation of an agentic artificial intelligence system for automated data extraction from anonymized Lithuanian pathology reports. The goal is to convert unstructured clinical narrative into structured records that follow International Collaboration on Cancer …
-
Design of agentic ai systems for automated data extraction in medical processes /
… thesis examines the design and evaluation of an agentic artificial intelligence system for automated data extraction from anonymized Lithuanian pathology reports. The goal is to convert unstructured clinical narrative into structured records that follow International Collaboration on Cancer …
-
CLOUD-BASED AND FULLY LOCALIZED OFFENSIVE AGENTIC AI FRAMEWORK FOR SECURE PENETRATION TESTING
… traditional penetration testing approaches strain cybersecurity analysts, which directly impacts the operational readiness of defense networks. This thesis explores two implementations of human-supervised, AI agentic frameworks that both address operator fatigue while maintaining the mandatory …
-
Building Trustworthy Machine Learning Systems for Security: From Federated Learning to Agentic AI
… enabling distributed devices to jointly train models without sharing raw data. This dissertation addresses critical challenges in building trustworthy and secure machine learning systems across two complementary frontiers: FL systems for network and medical security, and anomaly detection …
-
Can an Agentic AI System Increase Willingness to Engage with Support Services in Wales?
… or are nervous about how to start. This study aims to develop an agentic AI system capable of eligibility assessment, population of application form fields, and complete annotated PDF form generation. The system presents an easy-to-use conversational interface that employs a non-linear workflow …
-
Evaluating Agentic AI for Code Generation in Earth Observation and Thermal Remote Sensing Domains
Τα συστήματα Τεχνητής Νοημοσύνης με αυτόνομους πράκτορες διερευνώνται ολοένα και περισσότερο ως εργαλεία υποστήριξης σύνθετων αναλυτικών ροών σε επιστημονικούς και τεχνικούς τομείς. Στην Παρατήρηση της Γης (Earth Observation – EO) και τη θερμική τηλεπισκόπηση, η αξιόπιστη παραγωγή κώδικα για το …
-
Agentic AI-Driven Strategic Bidding of Battery Energy Storage Systems under Electricity Market Uncertainty
… of profitable bidding strategies for BESSs remains fundamentally challenging due to multiple sources of uncertainty. First, electricity markets are inherently uncertain, characterized by stochastic market prices and conditions that are difficult to forecast accurately. Second, market outcomes …
-
Agentic AI systems in professional domains: A probabilistic framework for role suitability and legal accountability
This thesis presents a cross-sector analysis of agentic AI systems deployed in STEM, education, healthcare, and enterprise domains, with a focus on role suitability, orchestration maturity, and legal accountability. It introduces the Bounded Agentic Suitability Envelope, a dual-bound scoring …
-
When Agents Spend Watts: Measuring Performance-Energy Trade-offs in Agentic AI Systems with AgenticBench
Agentic AI systems increasingly transform a single user request into a multi-step workflow of reasoning, tool use, retries, and framework coordination. Standard benchmark reporting emphasizes task accuracy, but this can hide the latency and energy-related cost of producing an answer. This thesis …
-
METHODOLOGICAL INNOVATIONS FOR CLINICAL RESEARCH: IMPROVING RELIABILITY, DATA SHARING, AND AGENTIC AI ACROSS THE EVIDENCE LIFECYCLE
Real-world data from electronic health records, claims databases, and other clinical sources offer an unprecedented opportunity to generate evidence about how care affects health. Realizing that opportunity requires confronting a set of persistent methodological challenges: observational studies …
-
Design and Development of a Socratic Intelligent Tutoring System: Leveraging Agentic AI for Asynchronous Online Learning
… can be effectively implemented using generative AI in a Retrieval Augmented Generation (RAG) based agentic system. The system, named "Gadfly," was developed using enterprise web services and designed around five core principles of Socratic methodology: defining terms, refutation (elenchus), …
Page 1 of 4