Skip to content
View tylerstennett's full-sized avatar
🎓
🎓
13 followers · 9 following

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report tylerstennett

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tylerstennett/README.md

Hey! Welcome to my profile 😄

My name is Tyler Stennett, and I'm a first-year computer science Ph.D. student at the Georgia Institute of Technology. I'm currently a member of Georgia Tech's Software Engineering Lab, advised by Professor Alessandro Orso. My research focuses on AI for software engineering, especially LLM- and agent-based approaches for automated software testing. I've also served as a research intern at IBM Research.

Projects

💻 I'm currently working on research at the intersection of large language models, software testing, program analysis, and autonomous agents.

📓 Much of my recent work explores how LLMs and agentic systems can improve automated software testing. This includes RESTGPT, published in ICSE-NIER 2024, and AutoRestTest, published as a research paper in ICSE 2025 and as a demonstration paper in ICSE-Demo 2025. I have also contributed to SAINT, an approach to service-level test generation using program analysis and LLM-based agents published in ICSE 2026 and Hamster, an empirical study on developer-written tests at scale published in ICSE-SEIP 2026.

🏠 Some of my earlier research includes human activity recognition for smart home environments, where I studied change point detection for smart home sensor data using supervised and unsupervised learning as part of my completed undergraduate thesis.

Thanks for reading, and feel free to reach out!

Pinned Loading

  1. selab-gatech/autoresttest selab-gatech/autoresttest Public

    Automated black-box REST API testing using graph-based modeling, LLMs, and multi-agent reinforcement learning.

    HTML 46 16

  2. selab-gatech/restgpt selab-gatech/restgpt Public

    LLM-powered tool that enhances OpenAPI specifications by extracting machine-readable constraints from human-readable descriptions.

    Java 14 7

  3. aster-test-generation/hamster-empirical-study aster-test-generation/hamster-empirical-study Public

    Large-scale empirical study analyzing 1.7M developer-written Java tests to characterize test scope, fixtures, assertions, inputs, and mocking patterns.

    Python 3 1

  4. conduit conduit Public

    A lightweight, provider-agnostic Python client for LLMs that unifies vLLM, Ollama, and OpenRouter behind a single async/sync interface with streaming, tool calling, and automatic retries

    Python 1

  5. lora-code-qa lora-code-qa Public

    PEFT for Code QA using DoRA

    Python 2

  6. trading-intelligence trading-intelligence Public

    LSTM, SVM, and linear regression for day-to-day stock price predictions

    Jupyter Notebook