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 40 for “"LLM agents"”.

  1. ENABLING LLM AGENTS TO CONTINUALLY PERCEIVE, LEARN, AND EVOLVE IN DIVERSE ENVIRONMENTS

    This thesis develops LLM-based agents that can perceive, learn, and evolve in structured, text- and multimodal-rich environments, combining language representations with structure-aware learning under realistic test-time constraints. For perception, we propose UniGraph, a self-supervised foundation …

    nus Repository record for ENABLING LLM AGENTS TO CONTINUALLY PERCEIVE, LEARN, AND EVOLVE IN DIVERSE ENVIRONMENTS (opens in a new tab) Download file for ENABLING LLM AGENTS TO CONTINUALLY PERCEIVE, LEARN, AND EVOLVE IN DIVERSE ENVIRONMENTS (opens in a new tab)

  2. Design and Gradient-Free Adaptation of Compound LLM Agents in a Partially Observable Adversarial Networked Environment

    … automated defenders. Large language models (LLMs) can read observations, reason, and act without task-specific training. This thesis studies how far an LLM-based defender can go in CAGE Challenge 2 (CAGE-2), a cyber-defense benchmark whose top solution is a gradient-trained reinforcement …

    carleton Repository record for Design and Gradient-Free Adaptation of Compound LLM Agents in a Partially Observable Adversarial Networked Environment (opens in a new tab)

  3. Self-Improving LLM Contexts for Agentic AI

    Large language model (LLM) agents have become increasingly capable systems for solving complex tasks through reasoning, tool use, and interaction with external environments. Recent work has shown that the LLM agents can be improved not only through parameter fine-tuning, but also through modifying …

    chalmers Repository record for Self-Improving LLM Contexts for Agentic AI (opens in a new tab)

  4. Predicting the Need for Test Maintenance Using LLM Agents - Applying Test Maintenance Factors to Changes in Production Code to Identify If and Where Test Cases Need to Be Updated

    … well. Generative AI and Large Language Models (LLMs) offer new avenues for automation and lessening the test maintenance problem. One of these is through LLM agents, sophisticated AI systems that reason, plan, and use tools to help it achieve its goals. This thesis was conducted as an …

    chalmers Repository record for Predicting the Need for Test Maintenance Using LLM Agents - Applying Test Maintenance Factors to Changes in Production Code to Identify If and Where Test Cases Need to Be Updated (opens in a new tab)

  5. STOCHASTIC OPTIMIZATION FOR DISTRIBUTED TRAINING AND MULTI-AGENT INTERACTION IN LARGE LANGUAGE MODELS

    … training and coordinating Large Language Models (LLMs) in distributed settings. We study two interconnected problems: (i) controlling the training dynamics of LLMs across distributed datasets, and (ii) modeling and controlling emergent behaviors when multiple LLM agents interact over networks. …

    cornell Repository record for STOCHASTIC OPTIMIZATION FOR DISTRIBUTED TRAINING AND MULTI-AGENT INTERACTION IN LARGE LANGUAGE MODELS (opens in a new tab)

  6. From Alarms to Root-Cause: Autonomous Hardware Diagnostics through Multi-Agent Systems: A feasibility evaluation and proof-of-concept for LLM based diagnostics

    The rapid adoption of large language models (LLMs) and by extension LLM agents is transforming the way work is done across various industrial sectors. Although systemic performance increases are promised across many white-collar domains, certain areas that could leverage the technology remain …

    chalmers Repository record for From Alarms to Root-Cause: Autonomous Hardware Diagnostics through Multi-Agent Systems: A feasibility evaluation and proof-of-concept for LLM based diagnostics (opens in a new tab)

  7. Design and Evaluation of Autonomous Language Agents in Scientific Discovery and Clinical Reasoning

    … and collaborative Large Language Model (LLM) agents within scientific discovery and clinical reasoning workflows. It first presents Agent Laboratory, a multi-agent system utilizing mle-solver and paper-solver modules for experimentation and report generation. Evaluations demonstrate that …

    jhu Repository record for Design and Evaluation of Autonomous Language Agents in Scientific Discovery and Clinical Reasoning (opens in a new tab)

  8. HIVEMIND: MULTI-AGENT LARGE LANGUAGE MODELS FOR OFFLINE SOFTWARE DEVELOPMENT

    General large language models’ (LLMs) ability to process natural language requests and return sound output to users has been revolutionary. Still, it comes at the cost of extensive computing power, reliable internet connections, and time. This thesis creates a system, HIVEMIND, that explores the …

    nps Repository record for HIVEMIND: MULTI-AGENT LARGE LANGUAGE MODELS FOR OFFLINE SOFTWARE DEVELOPMENT (opens in a new tab)

  9. Didžiųjų kalbos modelių grįstų agentinių sistemų projektavimo sprendimų ir reikalavimų įtaka jų realizacijai ir naudotojo sąveikai /

    … examines the design of a large language model (LLM) based agentic system through a case study. The object of investigation is a self-developed prototype -- an automotive parts inquiry system with an LLM agent interface integrated with the external TecDoc catalogue. First, following …

    vilnius Repository record for Didžiųjų kalbos modelių grįstų agentinių sistemų projektavimo sprendimų ir reikalavimų įtaka jų realizacijai ir naudotojo sąveikai / (opens in a new tab)

  10. Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach

    … architecture with two specialized LLM agents: a Teaching Agent for dynamic interaction and a Lesson Planning Agent for lesson generation. The system is designed to adapt to individual student needs, with interactions meticulously tracked and stored in a knowledge graph. This graph …

    odu Repository record for Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach (opens in a new tab)

  11. Detect, Explain, Ground: A Sustainable Pipeline for Robust Large Language Model–Powered Agents

    Large language models (LLMs) enable fluent dialogue but still suffer from critical breakdowns, such as incoherence, irrelevance, or factual inaccuracies (hallucinations). This thesis develops a sustainable, three-stage pipeline to detect, manage, and ground LLM-powered agents, enhancing their …

    queens Repository record for Detect, Explain, Ground: A Sustainable Pipeline for Robust Large Language Model–Powered Agents (opens in a new tab)

  12. Advancing reasoning and planning in large language models via reward shaping

    Recent advancements in large language models (LLMs) have significantly enhanced their reasoning and planning capabilities, enabling them to serve effectively in complex, real-world scenarios. Despite these improvements, achieving human-level performance remains challenging, particularly for tasks …

    gatech Repository record for Advancing reasoning and planning in large language models via reward shaping (opens in a new tab)

  13. Interpretable and Trustworthy AI Systems for Healthcare

    … models. With advances in large language models, LLM-based agents hold substantial potential for healthcare tasks. However, healthcare data is sensitive and any leakage or corruption has a direct impact on patients, and AI systems must comply with regulations such as HIPAA and GDPR. Therefore, we …

    duke Repository record for Interpretable and Trustworthy AI Systems for Healthcare (opens in a new tab)

  14. Towards Reliable and Practical Language-Model Agents: Evaluation and Development

    While Large Language Model (LLM) agents with complex reasoning and tool-use capabilities are promising, their fundamental unreliability like hallucination hinders practical, high-stakes deployment. This thesis confronts this gap by diagnosing key facets of this unreliability and proposing a more …

    toronto-retro Repository record for Towards Reliable and Practical Language-Model Agents: Evaluation and Development (opens in a new tab)

  15. Teaching AIs to Reason and Code, Confidentially

    Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that …

    houston Repository record for Teaching AIs to Reason and Code, Confidentially (opens in a new tab)

  16. Akcijų prekybos automatizavimas panaudojant dideliu kalbos modeliu grindžiamą prekybos agentą /

    … trading system based on Large Language Model (LLM) agents. The research begins with a comprehensive analysis of investment theories, AI literature, and the history of trading automation. In the practical part of the work, six distinct LLM-based prototypes were developed and tested through …

    vilnius Repository record for Akcijų prekybos automatizavimas panaudojant dideliu kalbos modeliu grindžiamą prekybos agentą / (opens in a new tab)

  17. Enhancing Credit Path Planning With LLM-Based Multi-Agent Systems

    … applying Multi-Agent (MA) Large Language Models (LLMs) to enhance credit card management, an underexplored area for their multi-step reasoning capabilities. Focusing on Equifax’s Optimal Path™ model [1]—a personalized solution for credit score optimization—the study addresses two key challenges: …

    kennesaw Repository record for Enhancing Credit Path Planning With LLM-Based Multi-Agent Systems (opens in a new tab)

  18. PERSEVERANCE: Predictive Engineering with Resilient Simulation and AI-Enabled Reasoning

    … (RAG) and task-specific large language model (LLM) agents to support maintenance request intake, hazard identification, and automated work package generation. System performance is evaluated in terms of retrieval accuracy, document completeness, and planning efficiency, demonstrating that …

    utk-theses Repository record for PERSEVERANCE: Predictive Engineering with Resilient Simulation and AI-Enabled Reasoning (opens in a new tab)

Page 1 of 2