Physical Sciences and Mathematics Commons^™

Exploring Autonomous Agents: A Closer Look At Why They Fail When Completing Tasks, Ruofan Lu, Yichen Li, Yintong Huo

Research Collection School Of Computing and Information Systems

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the interactions, communication mechanisms, and failure causes within these systems. To bridge this gap, we present a benchmark of 34 representative programmable tasks designed to rigorously assess autonomous agents. Using this benchmark, we evaluate three popular open-source agent frameworks combined with two LLM backbones, observing a task completion rate of approximately 50%. Through in-depth failure analysis, we develop a three-tier taxonomy of failure causes aligned with task phases, highlighting planning errors, task …

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo

Research Collection School Of Computing and Information Systems

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., ”center the logo”) remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs …

Image Captioning Through The Lens Of The Gricean Maxims: Generating Meaningful And Relevant Image Descriptions, Annika Lindh

Doctoral

Image captioning models enable us to automatically generate natural language image descriptions for previously unseen images. It combines the two fields of computer vision and natural language generation, allowing models to interpret the con tent of an image and communicate that knowledge through natural language text.

Research into image captioning has the potential benefit of reducing the gap in digital information availability between fully sighted individuals and those who are visually impaired. However, automatically generated captions often fail to provide the required level of detail and specificity to achieve this goal. Furthermore, current standard evaluation methods are insufficient at measuring …

Does Generative Ai Facilitate Investor Trading? Early Evidence From Chatgpt Outages, Qiang Cheng, Pengkai Lin, Yue Zhao

Research Collection School Of Accountancy

In this paper, we use ChatGPT outages to provide early evidence on whether investors rely on generative artificial intelligence (GenAI) to perform professional tasks and the associated impact on stock price informativeness. We document a significant decline in stock trading volume during ChatGPT outages. The effect is stronger for firms with corporate news released immediately before or during the outages and for firms with higher ownership held by transient institutional investors. We then document declines in short-run price impact and return variance during the outage periods, consistent with reduced informed trading. Lastly, we document a positive effect of GenAI-assisted trading …

Branch-And-Cut-And-Price For Agile Earth Observation Satellite Scheduling, Guansheng Peng, Jianjiang Wang, Guopeng Song, Aldy Gunawan, Lining Xing, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

The Agile Earth Observation Satellite scheduling selects and sequences satellite observations of possible targets on the Earth’s surface, each with a specific profit and multiple time windows. The objective is to maximize the collected profit of all observations completed under some operational constraints. The problem can be modeled as a variant of the Team Orienteering Problem with Time Windows (TOPTW). The key differences with the regular TOPTW are twofold: first, a time-dependent transition time is required for each pair of consecutive observations to adjust the camera’s look angles. Second, the time windows of each target vary during different observation cycles, …

Universal Crackling Noise Links Plasticity In Nanoindentation With Compression In Metallic Glasses, Jordan Sickle, Wesley H. Higgins, Kerry A. Baker, Mayisha Nakib, Xiaojun Gu, George M. Pharr, Wendelin Wright, Karin A. Dahmen

Faculty Journal Articles

For decades, compression tests have been a standard method for identifying materials properties. However, these tests are slow, destructive, and require fabricating multiple potentially expensive bulk samples. Nanoindentation is fast, almost non-destructive, and requires only a single sample, to which large numbers of indents can be applied. Furthermore, nanoindentation is widely applicable, even to materials that are too brittle for traditional compression tests. Here, we show that nanoindentation is sufficient for extracting much of the same information that is measured in traditional sample compression tests in metallic glasses. The dynamics and statistics of the plasticity of two types of metallic …

Draft 2026 Interim Site-Wide Groundwater Monitoring Quality Assurance Project Plan, Woodard & Curran

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft 2026 Interim Site-Wide Surface Water Monitoring Quality Assurance Project Plan, Woodard & Curran

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Butte Priority Soils Operable Unit Clark Tailings Consolidated Waste Management Area Site Investigation Quality Assurance Project Plan (Qapp) Revision 0, Woodard & Curran

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Ecophysiological Benefits Of Industrial Organic Wastes On Alfalfa Yield And Stress Mitigation In Saline Soils, Shugao Fan, Zhuanzhuan Ma, Jiawei Wu, Tianhui Yang, Jincheng Hao, Shumei Chen, Xutong Hu, Ying Zhao

School of Mathematical & Statistical Sciences Faculty Publications

Rising soil salinity and water scarcity demand sustainable solutions to maintain crop productivity. This study evaluated four agro-industrial organic amendments—fish emulsion, neem cake, coffee grounds, and seaweed extract on alfalfa (Medicago sativa) under combined salinity and drought stress, assessing their effects on soil respiration, plant physiology, and yield. Soil CO₂ efflux varied significantly among treatments: coffee grounds induced the highest microbial activity (6.2 μmol m⁻² s⁻¹), suggesting rapid decomposition, while neem cake exhibited stable emissions (3.8 μmol m⁻² s⁻¹), indicating slower organic matter turnover. Fish emulsion showed intermediate dynamics, peaking at 4.8 μmol m⁻² s⁻¹ by week 4, …

Addressing Sparsity For Knowledge Graph Completion: Data And Model Perspectives, Ran Liu

Dissertations and Theses Collection (Open Access)

Knowledge graphs (KGs) are powerful tools for structuring factual knowledge into relational triples, yet their practical utility is often adversely affected by data sparsity. Many entities and relations are associated with only a few observations, which limits the quality of learned embeddings and weakens generalization in downstream tasks. The problem of sparsity led to two interrelated challenges. Firstly, it restricts the informativeness of training samples: positive examples are scarce, and conventional negative sampling often produces trivial or redundant negatives that resulting in limited guidance. Secondly, in few-shot relation learning scenarios, sparsity worsens distribution shifts between training and test relations, as …

Gw241011 And Gw241110: Exploring Binary Formation And Fundamental Physics With Asymmetric, High-Spin Black Hole Coalescences, A. G. Abac, I. Abouelfettouh, Teviet Creighton, Mario C. Diaz, R. Espinosa, J. Lawrence, Francisco Llamas Villarreal, Soma Mukherjee, Volker Quetschke, Miriam Ramos Arevalo, Wenhui Wang

Physics & Astronomy Faculty Publications

We report the observation of gravitational waves from two binary black hole coalescences during the fourth observing run of the LIGO–Virgo–KAGRA detector network, GW241011 and GW241110. The sources of these two signals are characterized by rapid and precisely measured primary spins, nonnegligible spin–orbit misalignment, and unequal mass ratios between their constituent black holes. These properties are characteristic of binaries in which the more massive object was itself formed from a previous binary black hole merger and suggest that the sources of GW241011 and GW241110 may have formed in dense stellar environments in which repeated mergers can take place. As the …

The Ai-Powered Learning Loop In Higher Education, Oualid Abidi, Vladimir Dzenopoljac, Aleksandra Dzenopoljac

All Works

Purpose – This study examines how generative AI tools affect business students’ academic performance by investigating whether flexible AI policies promote deeper learning, enhance self-efficacy and facilitate tacit knowledge acquisition in a Middle Eastern context, while ensuring efficiency and academic integrity. Design/methodology/approach – A qualitative, exploratory study observed 20 final-year business students in Kuwait during five in-class activities using generative AI tools. Semi-structured interviews complemented the researcher’s observations. Thematic analysis revealed patterns in benefits, challenges and learning processes, leading to the development of the AI-powered learning loop framework to explain academic performance outcomes. Findings – The study indicates that generative …

Global Standards And Local Ambitions Across Green Taxonomies: Climate Change Mitigation From The European Union To South Africa, Theodor Florian Cojoianu, Andreas G. F. Hoepner, Ifigeneia Paliampelou, Anh Vu, Dariusz Wojcik

Research Collection College of Integrative Studies

Country-level green finance taxonomy standards have emerged to provide clarity on environmentally-sustainable economic activities to attract investment, protect financial services consumers, and counteract greenwashing. This paper adopts the Global Production and Financial Network (GPFN) approach and analyses factors affecting the climate change mitigation ambition level of the South African Green Finance Taxonomy (RSA GFT) in comparison with the EU taxonomy, which served as a model for South Africa's (RSA) regulators. It accounts for (i) the interplay between EU’s and RSA’s production and financial networks, and (ii) RSA’s willingness to attract European funding for sustainable development. We find that EU private …

Explainable Sentiment Analysis With Deepseek-R1: Performance, Efficiency, And Few-Shot Learning, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have transformed sentiment analysis, yet balancing accuracy, efficiency, and explainability remains a critical challenge. This study presents the first comprehensive evaluation of DeepSeek-R1—an open-source reasoning model—against OpenAI’s GPT-4o and GPT-4o-mini. We test the full 671B model and its distilled variants, systematically documenting few-shot learning curves. Our experiments show DeepSeek-R1 achieves a 91.39% F1 score on 5-class sentiment and 99.31% accuracy on binary tasks with just 5 shots, an eightfold improvement in few-shot efficiency over GPT-4o. Architecture-specific distillation effects emerge, where a 32B Qwen2.5-based model outperforms the 70B Llama-based variant by 6.69 percentage points. While its reasoning …

Sketch-Sparsenet: Sparse Convolution Framework For Sketch Recognition, Jingru Yang, Jin Wang, Yang Zhou, Guodong Lu, Yu Sun, Huan Yu, Heming Fang, Zhihui Li, Shengfeng He

Research Collection School Of Computing and Information Systems

In free-hand sketch recognition, state-of-the-art methods often struggle to extract spatial features from sketches with sparse distributions, which are characterized by significant blank regions devoid of informative content. To address this challenge, we introduce a novel framework for sketch recognition, termed Sketch-SparseNet. This framework incorporates an advanced convolutional component: the Sketch-Driven Dilated Deformable Block (SD3B). This component excels at extracting spatial features and accurately recognizing free-hand sketches with sparse distributions. The SD3B component innovatively bridges gaps in the blank areas of sketches by establishing spatial relationships among disconnected stroke points through adaptive reshaping of convolution kernels. These kernels are deformable, …

Sustainable Llm Inference For Edge Ai: Evaluating Quantized Llms For Energy Efficiency, Output Accuracy, And Inference Latency, Erik Johanne Husom, Arda Goknil, Merve Astekin, Lwin Khin Shar, Andre Kasen, Sagar Sen, Benedikt Andreas Mithassel, Ahmet Soylu

Research Collection School Of Computing and Information Systems

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on …

Generative Ai And Empirical Software Engineering: A Paradigm Shift, Christoph Treude, Margaret-Anne Storey

Research Collection School Of Computing and Information Systems

The widespread adoption of generative AI in software engineering marks a paradigm shift, offering new opportunities to design and utilize software engineering tools while influencing both developers and the artifacts they create. Traditional empirical methods in software engineering, including quantitative, qualitative, and mixed-method approaches, are well established. However, this paradigm shift introduces novel data types and redefines many concepts in the software engineering process. The roles of developers, users, agents, and researchers increasingly overlap, blurring the distinctions between these social and technical actors within the field. This paper examines how integrating AI into software engineering challenges traditional research paradigms. It …

Predict Social Economic Outcomes By Transferred Knowledge With Satellite Imagery, Yang Tang, Shih-Fen Cheng, Yunqiang Zhu, Yichen Yang, Zhiqiang Zou

Research Collection School Of Computing and Information Systems

Traditional deep learning methods and econometric models have played a crucial role in the field of data mining, particularly in the prediction of socioeconomic outcomes. However, socio-economic information is unable to be directly extracted from remote sensing data. So, in this paper, we propose a method to leverage transfer learning to predict socioeconomic indicators (outcomes) through satellite imagery. Specifically, we use road network types as a proxy for socioeconomic factors, which is more effective and stable than using nightlight. We have extracted eleven distinct road topological features to generate reasonable road network types. Given the unique characteristics of road networks, …

Enhancing Spatial Understanding In Mixed-Reality Presentations, Nam-Dang Vo, Van-Vinh Thai, Nam-Hoi Do, Viet-Tham Huynh, Anthony Tang, Khan-Duy Le

Research Collection School Of Computing and Information Systems

Mixed reality (MR) presentations often involve a presenter wearing a head-mounted display (HMD) and an audience watching via a large display, making it difficult for audiences to perceive spatial relationships between the presenter and virtual objects. We report two experiments testing three design variations: (1) scene camera placement (audience-aligned vs. opposite), (2) overlaying the presenter’s first-person view, and (3) highlighting objects in the presenter’s view. Results show that audience-aligned cameras and object highlighting improve spatial understanding, while combining third- and first-person views can further aid perception. We derive design guidelines for configuring MR presentations to better support audience comprehension.

Metacan: Improving Generalizability Of Few‑Shot Anomaly Detection With Meta‑Learning, Zhisheng Lv, Jianfeng Zhang, Songlei Jian, Chenlin Huang, Hongguang Zhang, Guansong Pang, Zhong Liu

Research Collection School Of Computing and Information Systems

Few-shot Anomaly Detection (AD) for images aims to detect anomalies with few-shot normal samples from the target dataset. It is a crucial task when only few samples can be obtained, and it is challenging since it needs to be generalized to different domains. Existing methods try to enhance the generalizability of AD by incorporating large vision-language models (LVLMs).However, how to transform category semantic information in LVLMs into anomaly information to improve the generalizability of AD remains a challenge facing existing methods.To address the challenge, we propose a few-shot AD method called MetaCAN, a novel category-to-anomaly network trained with AD meta-learning …

Uncovering The Values Of The Metaverse For Leisure Use By Individuals: A Value-Focused Thinking Approach, Ruilin Zheng, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

The metaverse is a computer-mediated environment where users take the form of digital avatars when participating in activities and interacting with one another. Given the popularity of the metaverse, especially among the younger population, we identified the values offered by the metaverse for leisure use by its users. Using the Value-Focused Thinking (VFT) approach, we identified these values in the form of fundamental and means objectives. The VFT approach was applied in interviewing users who conduct leisure activities in the metaverse and in analyzing the data collected. A total of 27 metaverse users were interviewed, which generated 8 fundamental objectives …

International Workshop On Multimodal Generative Search And Recommendation (Mmgensr@Cikm 2025), Yi Bin, Haoxuan Li, Haokai Ma, Yang Zhang, Wenjie Wang, Yunshan Ma, Yang Yang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Recent breakthroughs in generative Artificial Intelligence (AI) have ignited a revolutionary wave across information retrieval and recommender systems. This workshop serves as a premier interdisciplinary platform to explore how generative models, particularly Large Language Models (LLMs) and Large Multimodal Models (LMMs), are transforming multimodal search and recommendation paradigms [3, 6, 9, 10, 12-14]. We aim to convene researchers and practitioners to discuss innovative architectures, methodologies, and evaluation strategies spanning generative document retrieval [5, 8] generative image retrieval [ 7, 16], grounded answer generation [17], generative recommendation [2, 4, 11], and related tasks involving multiple modalities [1,15]. The workshop will facilitate …

Designing For Novice Debuggers: A Pilot Study On An Ai-Assisted Debugging Tool, Oka Kurniawan, Erick Chandra, Christopher M. Poskitt, Yannic Noller, Kenny T.W. Choo, Cyrille Jegourel

Research Collection School Of Computing and Information Systems

Debugging is a fundamental skill that novice programmers must develop. Numerous tools have been created to assist novice programmers in this process. Recently, large language models (LLMs) have been integrated with automated program repair techniques to generate fixes for students' buggy code. However, many of these tools foster an over-reliance on AI and do not actively engage students in the debugging process. In this work, we aim to design an intuitive debugging assistant, CodeHinter, that combines traditional debugging tools with LLM-based techniques to help novice debuggers fix semantic errors while promoting active engagement in the debugging process. We present findings …

Why Stop At One Error? Benchmarking Llms As Data Science Code Debuggers For Multi-Hop And Multi-Bug Errors, Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

Research Collection School Of Computing and Information Systems

LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs’ capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. …

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao

Research Collection School Of Computing and Information Systems

Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Unified Molecule Pre-Training With Flexible 2d And 3d Modalities: Single And Paired Modality Integration, Tengwei Song, Min Wu, Yuan Fang

Research Collection School Of Computing and Information Systems

Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture comprehensive structural and geometric insights. However, these methods require paired 2D and 3D molecular data to train the model effectively and prevent it from collapsing into a single modality, posing limitations in scenarios where a certain modality is unavailable or computationally expensive to generate. To overcome this limitation, we propose FlexMol, a flexible molecule pre-training framework that learns unified molecular representations while supporting single-modality input. Specifically, inspired by …

Security Modelling For Cyber-Physical Systems: A Systematic Literature Review, Shao Fei Huang, Christopher M. Poskitt, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Cyber-physical systems are at the intersection of digital technology and engineering domains, rendering them high-value targets of sophisticated and well-funded cybersecurity threat actors. Prominent cybersecurity attacks on CPS have brought attention to the vulnerability of these systems and the inherent weaknesses of critical infrastructure reliant on them. Security modelling for CPS is an important mechanism to systematically identify and assess vulnerabilities, threats, and risks throughout system life cycles, and to ultimately ensure system resilience, safety, and reliability. This survey delves into state-of-the-art research on CPS security modelling, encompassing both threat and attack modelling. While these terms are sometimes used interchangeably, …

Intentionframe: A Semi-Structured, Multi-Aspect Framework For Fine-Grained Conversational Intention Understanding, Zailong Tian, Zhuoheng Han, Lizi Liao, Lizi Liao

Research Collection School Of Computing and Information Systems

Understanding user intentions in multi-turn dialogues is critical for conversational AI, yet existing approaches—relying on rigid slot-value structures or unstructured free-text—fail to fully capture conversational complexity. In this paper, we propose IntentionFrame, a semi-structured framework inspired by psychological and cognitive intention theories, which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. This design not only retains interpretability but also provides LLMs with a rich context to accurately parse and respond to nuanced user inputs. To efficiently scale IntentionFrame annotations, we introduce a Weakly-supervised Reinforced Generation (WeRG) method that leverages a small set of high-quality human annotations …