Software Engineering Commons^™

Agentspec: Customizable Runtime Enforcement For Safe And Reliable Llm Agents, Haoyu Wang, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and unintended harmful actions. Existing mitigation methods, such as model-based safeguards and early enforcement strategies, fall short in robustness, interpretability, and adaptability. To address these challenges, we propose AgentSpec, a lightweight domain-specific language for specifying and enforcing runtime constraints on LLM agents. With AgentSpec, users define structured rules that incorporate triggers, predicates, and enforcement mechanisms, ensuring agents operate within predefined safety boundaries. We implement AgentSpec across multiple domains, including code execution, embodied agents, …

Conflogger: Enhance Systems’ Configuration Diagnosability Through Configuration Logging, Shiwen Shan, Yintong Huo, Yuxin Su, Zhining Wang, Dan Li, Zibin Zheng

Research Collection School Of Computing and Information Systems

Modern configurable systems offer customization via intricate configuration spaces, yet such flexibility introduces pervasive configuration-related issues such as misconfigurations and latent softwarebugs. Existing diagnosability supports focus on post-failure analysis of software behavior to identify configuration issues, but none of these approaches look into whether the software clue sufficient failure information for diagnosis. To fill in the blank, we propose the idea of configuration logging to enhance existing logging practices at the source code level. We develop ConfLogger, the first tool that unifies configuration-aware static taint analysis with LLM-based log generation to enhance software configuration diagnosability. Specifically, our method 1) identifies …

Causality-Aware Safety Testing For Autonomous Driving Systems, Wenbing Tang, Mingfei Cheng, Renzhi Wang, Yuan Zhou, Chengwei Liu, Yang Liu, Zuohua Ding

Research Collection School Of Computing and Information Systems

Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different conditions. While existing methods typically focus on individual diversity metrics, such as input scenarios, ADS-generated motion commands, and system violations, they often fail to capture the complex interrelationships among these elements. For instance, identical motion commands can produce different collision risks in varying scenes, and the same collision may result from different commands under different scenarios. This oversight leads to gaps in testing coverage, potentially missing critical issues in the ADS …

On Autopilot? An Empirical Study Of Human-Ai Teaming And Review Practices In Open Source, Haoyu Gao, Peerachai Banyongrakkul, Hao Guan, Mansooreh Zahedi, Christoph Treude

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) increasingly automate software engineering tasks. While recent studies highlight the accelerated adoption of “AI as a teammate” in Open Source Software (OSS), developer interaction patterns remain under-explored. In this work, we investigated project-level guidelines and developers’ interactions with AI-assisted pull requests (PRs) by expanding the AIDev dataset to include finer-grained contributor code ownership and a comparative baseline of human-created PRs. We found that over 67.5% of AI-co-authored PRs originate from contributors without prior code ownership. Despite this, the majority of repositories lack guidelines for AI-coding agent usage. Notably, we observed a distinct interaction pattern: AI-co-authored PRs …

Fallen Light (Video Game), Joshua Do

Presentations - 2026

Problem:

•People misunderstand Lucifer’s deception

•(shown through Temptation of Jesus in Matthew 4) •Lack of engaging ways to teach theological concepts   •Background: Lucifer corrupts not through force, but subtle self-elevation and doubt   Motivation:   •Just initially wanted to make a game of how sin entered the world for fun   •Just thought it was a cool idea in general.

Solution:

•Dialogue-driven narrative game   •6+ story chapters   •10+ regions   •Focused on spiritual conflict, deception, and discernment   •Uses event-based progression   •Presents Lucifer through subtle manipulation, by being a false light by choosing self-pleasure over what is right.

Fisheasy, Jake Rankin

Presentations - 2026

Problem: 
Inexperienced and experienced anglers lack necessary tools to begin fishing

Motivation:
Fishing is a fun hobby everyone should be able to enjoy – the lack of resources makes that difficult

Solution:
An application that integrates learning tutorials with helpful practices tools for both novice and experienced anglers

Foxbuddy, Luis Eduardo Garza Jr.

Presentations - 2026

Problem:
•Many people are still unprepared incase of an emergency. (42%-46% are prepared for an emergency)
•Supplies can be scattered, expired, or forgotten.   •Reliable guidance is often not easy to access.

Fisheasy, Jake Ryan Rankin

Posters - 2026

The purpose of FishEasy is to create an all-in-one fishing application that supports both beginner and experienced anglers through education, recommendations, and data tracking. Many new anglers struggle with understanding gear, knots, bait, and locations, while existing tools often limit access through paid features. FishEasy addresses these gaps by providing:

• Educational Tutorials for knots, rigs, and beginner guidance • Smart Recommendations based on location, species, and conditions • Catch Logging & Analytics to track performance • Regulation Awareness for legal fishing practices


Overall, FishEasy aims to make fishing more accessible, efficient, and easy to learn for all users.

Spinlock Game Engine, Shane Misley

Posters - 2026

Modern game engines prioritize developer convenience at the cost of performance and transparency. Large frameworks like Unity and Unreal Engine abstract away implementation details, which simplifies development but introduces computational overhead—often 40-50% of CPU and memory usage goes to engine infrastructure rather than the actual game. For developers targeting low-end hardware, older systems, or performance-critical applications, this overhead becomes prohibitive. The Spinlock Engine addresses this problem by adopting a "close-to-the-metal" philosophy, stripping away unnecessary abstraction layers to deliver raw speed and predictable behavior. Built in C++ with SDL3 and Raylib, Spinlock prioritizes memory efficiency, CPU optimization, and developer transparency—allowing you …

Sentra, David Aguilar

Posters - 2026

In the fast-paced space of event organization, fostering continuous collaboration among participants is essential. However, organizers often lose valuable time monitoring multiple, disconnected systems once an event is underway. Enter Sentra: an all-in-one Discord bot tailored specifically for weekend events like hackathons. Sentra bridges the gap between participants and organizers by consolidating seamless team matchmaking, robust support ticketing, and automated AI moderation into a single, unified interface.

Synapse, Nicolas Diaz, Alexander Murphy, Sonia Cerrillo, Naomi Ramirez, Jesse Kemmer

Posters - 2026

People tend to accumulate a great deal of notes throughout their lives with no coherent way to organize them. Even with the built-in notes app, the notes eventually accumulate until it becomes borderline impossible to find what is needed. Our proposed solution is Synapse, an LLM powered notes app with a tagging system that allows notes to be sorted by topic. The LLM will be able to read the user's notes and recommend tags

Chopchop: The Digital Cookbook, Dominc Mcdevitt, Shane Misley, Adolfo Duran, Katie Cerda, Kobie Henson

Posters - 2026

Many of today's home chefs still use the same limited methods of saving recipes that have been used for decades, i.e. handwritten notes, disorganized pdfs, screenshots, saved text messages, etc. Not only are these formats hard to keep track of and easily lost, but they also suffer the risk of becoming irrevocably damaged or stained in the cooking process. They are also notoriously hard to edit, which limits a chef's ability to tailor recipes to their taste, their available ingredients, or even just a different serving size. Another major issue with these approaches is the lack of easy sharing. Giving …

Patchgpt: Multi-Agent Patch Backporting Without Model Fine-Tuning, Ye Liu, Ruidong Han, Chengyan Ma, Yuqing Niu, David Lo

Research Collection School Of Computing and Information Systems

Patch backporting is crucial and prevalent in the maintenance of modern open-source software such as Linux kernels and forked repositories. However, porting patches across program versions remains a challenging problem due to the complexity of synergizing diverse patches with divergent program versions. In this paper, we propose PatchGPT, an agentic patch backporting framework for fine-grained patch generation. PatchGPT encompasses three agents: Miner for decomposing a sequence of atomic change steps as the original patch plan, Adapter for adapting the patch plan, and Executor for executing the adapted patch plan according to predefined change semantics. We conduct experiments on the PPatHF’s …

Finding Missing Input Validation In Tees Via Llm-Assisted Symbolic Execution, Chengyan Ma, Jieke Shi, Ruidong Han, Ye Liu, Yuqing Niu, David Lo

Research Collection School Of Computing and Information Systems

Trusted Execution Environments (TEEs) provide hardware-enforced isolation that protects sensitive code and data from untrusted software. Despite their strong security guarantees, analyzing TEE applications remains challenging due to the high cost and complexity of configuring complete TEE build and runtime environments, as well as the limited observability imposed by hardware isolation. This paper presents SymTEE, a novel large language model (LLM)-assisted symbolic execution framework for detecting missing input validation issues in TEE applications without requiring real TEE setups. SymTEE begins by leveraging Abstract Syntax Tree (AST) analysis to extract TEE code slices that may lack sufficient input validation, and then …

Context Engineering For Ai Agents In Open-Source Software, Seyedmoein Mohsenimofidi, Matthias Galster, Christoph Treude, Sebastian Baltes

Research Collection School Of Computing and Information Systems

GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual information to develop solutions that are in line with the standards, policies, and workflows of the software projects they operate in. Vendors of popular agentic tools (e.g., Claude Code) recommend maintaining version-controlled Markdown files that describe aspects such as the project structure, code style, or building and testing. The content of these files is then automatically added to each prompt. Recently, AGENTS.md has emerged as a potential standard that …

Intelligent Deep Learning-Based Sign Language Translation System, Nada Rasem Shahin

Dissertations

The Deaf and Hard of Hearing (DHH) community uses sign language as a primary means of communication. However, the shortage of sign language interpreters and the existence of hundreds of sign languages limit accessibility and inclusion. Sign Language Machine Translation (SLMT) systems present a promising solution for bridging the communication gap between the DHH and the hearing individuals, supporting inclusive societies. In smart cities, such systems play an essential role in improving the quality of life on a community level. In particular, as the population’s well-being is critical, developing intelligent assistive technologies, such as SLMT systems, is necessary to provide …

Llm-Driven Mission Control And Autonomous Planning For Search-And-Rescue Uavs: A Simulation-Based Evaluation, Naser Bader Alsaedi

Theses

Unmanned aerial vehicles (UAVs) are increasingly used in search‑and‑rescue (SAR) missions, yet many systems still rely on fragmented software where mission design, perception, and flight control are configured separately. This thesis examines whether a unified AI‑driven framework can reduce configuration effort and operator workload in UAV‑based SAR operations. The proposed system integrates natural‑language mission specification using a large language model (LLM) (LLaMA 3.1), autonomous coverage planning, YOLOv8‑based victim detection, and PX4/MAVSDK control within a single architecture. Operators describe missions through free‑form text or a graphical interface; the model converts these descriptions into structured mission parameters that are automatically planned and …

Rethinking Artifact Evaluation For Software Engineering In The Age Of Generative Ai, Christoph Treude, Christopher M. Poskitt, Rashina Hoda

Research Collection School Of Computing and Information Systems

Peer review in software engineering research operates under tight time constraints, while generative AI has substantially reduced the human effort required to produce polished research narratives. Reviewer attention is often spent on aspects of submissions such as writing quality or literature positioning that have become relatively less effort-intensive to address, rather than on evaluating the scientific substance of a paper. At the same time, assessing whether methods are implemented correctly, analyses are sound, and claims are supported by evidence remains effort-intensive and dependent on human expertise. In software engineering research, this substance is frequently embodied in artifacts, including code, data, …

Who Said Cve? How Vulnerability Identifiers Are Mentioned By Humans, Bots, And Agents In Pull Requests, Pien Rooijendijk, Christoph Treude, Mairieli Wessel

Research Collection School Of Computing and Information Systems

Vulnerability identifiers such as CVE, CWE, and GHSA are standardised references to known software security issues, yet their use in practice is not well understood. This paper compares vulnerability ID use in GitHub pull requests authored by autonomous agents, bots, and human developers. Using the AIDev pop dataset and an augmented set of pull requests from the same repositories, we analyse who mentions vulnerability identifiers and where they appear. Bots account for around 69.1% of all mentions, usually adding few identifiers in pull request descriptions, while human and agent mentions are rarer but span more locations. Qualitative analysis shows that …

Bridging Bug Localization And Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models, Jianming Chang, Xin Zhou, Lulu Wang, David Lo, Bixin Li

Research Collection School Of Computing and Information Systems

Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques predominantly focus on the repair phase, often overlooking the importance of improving the preceding bug localization phase. As a foundational step in issue fixing, bug localization plays a pivotal role in determining the overall effectiveness of the entire process. To enhance the precision of issue fixing by accurately identifying bug locations in large-scale projects, this paper presents BugCerberus, the first hierarchical bug localization framework powered by three customized large language models. First, BugCerberus analyzes intermediate representations …