Digital Commons Network^™

Llm-Based Multi-Agent Systems For Software Engineering: Literature Review, Vision And The Road Ahead, Junda He, Christoph Treude, David Lo

Research Collection School Of Computing and Information Systems

Integrating Large Language Models (LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities that are competitive with human planning and reasoning. This paper explores the transformative potential of integrating Large Language Models into Multi-Agent (LMA) systems for addressing complex challenges in software engineering (SE). By leveraging the collaborative and specialized abilities of multiple agents, LMA systems enable autonomous problem-solving, improve robustness, and provide scalable solutions for managing the complexity of real-world software projects. In this paper, we conduct a systematic review of recent primary studies to map the current landscape of LMA applications …

Runtime Anomaly Detection For Drones: An Integrated Rule-Mining And Unsupervised Learning Approach, Ivan Wei Han Tan, Wei Minn, Christopher M. Poskitt, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, have witnessed a remarkable surge in popularity due to their versatile applications. These cyber-physical systems depend on multiple sensor inputs, such as cameras, GPS receivers, accelerometers, and gyroscopes, with faults potentially leading to physical instability and serious safety concerns. To mitigate such risks, anomaly detection has emerged as a crucial safeguarding mechanism, capable of identifying the physical manifestations of emerging issues and allowing operators to take preemptive action at runtime. Recent anomaly detection methods based on LSTM neural networks have shown promising results, but three challenges persist: the need for models …

Diversity Optimization For Travelling Salesman Problem Via Deep Reinforcement Learning, Qi Li, Zhiguang Cao, Yining Ma, Yaoxin Wu, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution TSP (MSTSP), we propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy. Concretely, on the one hand, a Relativization Filter (RF) is designed to enhance the robustness of the encoder to affine transformations of the instances, so as to potentially improve the quality of the found solutions. On the other hand, a Multi-Attentive Adaptive Active Search (MA3S) is tailored to allow the decoders to strike a …

An Efficient Diffusion-Based Non-Autoregressive Solver For Traveling Salesman Problem, Mingzhao Wang, You Zhou, Zhiguang Cao, Yubin Xiao, Xuan Wu, Wei Pang, Yuan Jiang, Hui Yang, Peng Zhao, Yuanshu Li

Research Collection School Of Computing and Information Systems

Recent advances in neural models have shown considerable promise in solving Traveling Salesman Problems (TSPs) without relying on much hand-crafted engineering. However, while non-autoregressive (NAR) approaches benefit from faster inference through parallelism, they typically deliver solutions of inferior quality compared to autoregressive ones. To enhance the solution quality while maintaining fast inference, we propose DEITSP, a diffusion model with efficient iterations tailored for TSP that operates in a NAR manner. Firstly, we introduce a one-step diffusion model that integrates the controlled discrete noise addition process with self-consistency enhancement, enabling optimal solution prediction through simultaneous denoising of multiple solutions. Secondly, we …

Milpbench: A Large-Scale Benchmark Test Suite For Mixed Integer Linear Programming Problems, Huigen Ye, Yaoyang Cheng, Hua Xu, Zhiguang Cao, Hanzhang Qin

Research Collection School Of Computing and Information Systems

Mixed-integer linear programming (MILP) is a cornerstone of optimization with applications across numerous domains. However, the development and evaluation of MILP-solving algorithms are hindered by existing benchmark datasets, which are often limited in scale, lack diversity, and are poorly structured, making them inadequate for systematic testing across different solving approaches, especially for machine learning (ML)-based methods. To address these issues, we introduce MILPBench, a large-scale benchmark suite comprising 100,000 MILP instances organized into 60 well-categorized classes. Using structural properties and embedding similarity metrics, we developed a novel classification framework to ensure both intra-class homogeneity and inter-class diversity. In addition to …

Surrogate Learning In Meta-Black-Box Optimization: A Preliminary Study, Zeyuan Ma, Zhiyang Huang, Jiacheng Chen, Zhiguang Cao, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Recent Meta-Black-Box Optimization (MetaBBO) approaches have shown possibility of enhancing the optimization performance through learning meta-level policies to dynamically configure low-level optimizers. However, existing MetaBBO approaches potentially consume massive function evaluations to train their meta-level policies. Inspired by the recent trend of using surrogate models for cost-friendly evaluation of expensive optimization problems, in this paper, we propose a novel MetaBBO framework which combines surrogate learning process and reinforcement learning-aided Differential Evolution algorithm, namely Surr-RLDE, to address the intensive function evaluation in MetaBBO. Surr-RLDE comprises two learning stages: surrogate learning and policy learning. In surrogate learning, we train a Kolmogorov-Arnold Networks …

A Mixed-Curvature Based Pre-Training Paradigm For Multi-Task Vehicle Routing Solver, Suyu Liu, Zhiguang Cao, Shanshan Feng, Yew-Soon Ong

Research Collection School Of Computing and Information Systems

Solving various types of vehicle routing problems (VRPs) using a unified neural solver has garnered significant attentions in recent years. Despite their effectiveness, existing neural multi-task solvers often fail to account for the geometric structures inherent in different tasks, which may result in suboptimal performance. To address this limitation, we propose a curvature-aware pre-training framework. Specifically, we leverage mixed-curvature spaces during the feature fusion stage, encouraging the model to capture the underlying geometric properties of each instance. Through extensive experiments, we evaluate the proposed pre-training strategy on existing neural multi-task solvers across a variety of testing scenarios. The results demonstrate …

Information Bottleneck‑Guided Mlps For Robust Spatial‑Temporal Forecasting, Min Chen, Guansong Pang, Wenjun Wang, Cheng Yan

Research Collection School Of Computing and Information Systems

Spatial-temporal forecasting (STF) plays a pivotal role in urban planning and computing. Spatial-Temporal Graph Neural Networks (STGNNs) excel at modeling spatial-temporal dynamics, thus being robust against noise perturbations. However, they often suffer from relatively poor computational efficiency. Simplifying the architectures can improve efficiency but also weakens robustness with respect to noise interference. In this study, we investigate the problem: can simple neural networks such as Multi-Layer Perceptrons (MLPs) achieve robust spatial-temporal forecasting while remaining efficient? To this end, we first reveal the dual noise effect in spatial-temporal data and propose a theoretically grounded principle termed Robust Spatial-Temporal Information Bottleneck (RSTIB), …

Quantum Technologies In Decentralisation, Paul Robert Griffin, Rudy Raymond, Tsuyoshi Idé

Research Collection School Of Computing and Information Systems

Quantum technologies, rooted in the manipulation of quantum information, are revolutionizing computing and networking domains. Their impact on blockchains and decentralized systems is twofold. While much attention has been given to the potential of quantum computing to attack blockchains, these advanced technologies also offer avenues for strengthening and optimizing them. This chapter delves into the intricacies of quantum technologies, from the foundational concepts of qubits, quantum gates, and quantum networks to their implications for blockchains. We explore both the vulnerabilities of blockchains in a quantum-dominant era and the promising solutions quantum technologies provide, culminating in a use case examining their …

Finir: The 2nd Workshop On Financial Information Retrieval In The Era Of Generative Ai, Fengbin Zhu, Yunshan Ma, Fuli Feng, Chao Wang, Huanbo Luan, Guangnan Ye, Shuo Zhang, Dhagash Mehta, Pingping Chen, Bing Xiang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Recent advancements in Generative AI, such as Large Language Models (LLMs), have demonstrated remarkable success across various general tasks. Extensive studies have explored leveraging generative models in finance, but significant challenges persist. This half-day workshop explores potential approaches and research directions to address these challenges by equipping generative models with advanced Information Retrieval (IR) models. Specifically, this workshop seeks to provide a platform for discussing innovative ideas that facilitate the advancement of IR technology to enrich generative models in finance from four key perspectives: (i) financial IR techniques (ii) financial IR benchmarking and evaluation (iii) financial systems and agents/assistants (iv) …

Cracking Aegis: An Adversarial Llm-Based Game For Raising Awareness Of Vulnerabilities In Privacy Protection, Jiaying Fu, Yiyang Lu, Zehua Yang, Fiona Fui-Hoon Nah, Ray Lc

Research Collection School Of Computing and Information Systems

Traditional methods for raising awareness of privacy protection often fail to engage users or provide hands-on insights into how privacy vulnerabilities are exploited. To address this, we incorporate an adversarial mechanic in the design of the dialogue-based serious game Cracking Aegis. Leveraging LLMs to simulate natural interactions, the game challenges players to impersonate characters and extract sensitive information from an AI agent, Aegis. A user study (n=22) revealed that players employed diverse deceptive linguistic strategies, including storytelling and emotional rapport, to manipulate Aegis. After playing, players reported connecting in-game scenarios with real-world privacy vulnerabilities, such as phishing and impersonation, and …

Exploring The Capabilities Of Llms For Code-Change-Related Tasks, Lishui Fan, Jiakun Liu, Zhongxin Liu, David Lo, Xin Xia, Shanping Li

Research Collection School Of Computing and Information Systems

Developers deal with code-change-related tasks daily, e.g., reviewing code. Pre-trained code and code-change-oriented models have been adapted to help developers with such tasks. Recently, large language models (LLMs) have shown their effectiveness in code-related tasks. However, existing LLMs for code focus on general code syntax and semantics rather than the differences between two code versions. Thus, it is an open question how LLMs perform on code-change-related tasks.To answer this question, we conduct an empirical study using 1B parameters LLMs on three code-change-related tasks, i.e., code review generation, commit message generation, and just-in-time comment update, with in-context learning (ICL) and parameter-efficient …

Explaining Explanations: An Empirical Study Of Explanations In Code Reviews, Ratnadira Widyasari, Ting Zhang, Abir Bouraffa, Walid Maalej, David Lo

Research Collection School Of Computing and Information Systems

Code reviews are central for software quality assurance. Ideally, reviewers should explain their feedback to enable authors of code changes to understand the feedback and act accordingly. Different developers might need different explanations in different contexts. Therefore, assisting this process first requires understanding the types of explanations reviewers usually provide. The goal of this article is to study the types of explanations used in code reviews and explore the potential of Large Language Models (LLMs), specifically ChatGPT, in generating these specific types. We extracted 793 code review comments from Gerrit and manually labeled them based on whether they contained a …

How Are We Detecting Inconsistent Method Names? An Empirical Study From Code Review Perspective, Kisub Kim, Xin Zhou, Dongsun Kim, Julia Lawall, Kui Liu, Tegawendé F. Bissyandé, Jacques Klein, Jaekwon Lee, David Lo

Research Collection School Of Computing and Information Systems

Proper naming of methods can make program code easier to understand, and thus enhance software maintainability. Yet, developers may use inconsistent names due to poor communication or a lack of familiarity with conventions within the software development lifecycle. To address this issue, much research effort has been invested into building automatic tools that can check for method name inconsistency and recommend consistent names. However, existing datasets generally do not provide precise details about why a method name was deemed improper and required to be changed. Such information can give useful hints on how to improve the recommendation of adequate method …

Enhancing Project-Specific Code Completion By Inferring Internal Api Information, Le Deng, Xiaoxia Ren, Chao Ni, Ming Liang, David Lo, Zhongxin Liu

Research Collection School Of Computing and Information Systems

Project-specific code completion, which aims to complete code based on the context of the project, is an important and practical software engineering task. The state-of-the-art approaches employ the retrieval-augmented generation (RAG) paradigm and prompt large language models (LLMs) with information retrieved from the target project for project-specific code completion. In practice, developers always define and use custom functionalities, namely internal APIs, to facilitate the implementation of specific project requirements. Thus, it is essential to consider internal API information for accurate project-specific code completion. However, existing approaches either retrieve similar code snippets, which do not necessarily contain related internal API information, …

Learning To Solving Vehicle Routing Problems Via Local-Global Feature Fusion Transformer, Wei Li, Bing Tian Dai, Xueming Yan, Junying Zou, Zhijie Liang, Jingwen Li

Research Collection School Of Computing and Information Systems

Applying Combinatorial optimization problems such as the Vehicle Routing Problems (VRPs) have attracted increasing interest with the emergence of learning-based methods. However, existing neural approaches often struggle to generalize across diverse problem sizes and node distributions, limiting their applicability in real-world scenarios. To overcome these challenges, we propose Local-Global Feature Fusion Transformer (FusionFormer), a novel deep reinforcement learning framework that enhances both solution quality and generalization capability for solving VRPs. Specifically, we introduce a Distance-Assisted Multi-Head Attention (DA-MHA) mechanism that incorporates explicit spatial distance information into the attention computation, thereby preserving spatial consistency and facilitating more robust global representation learning. …

Personal Bankruptcy: A Bibliometric Analysis And Future Research Directions, Aqilah Nadiah Md Sahiq, Saida Farhanah Sarkam, Putri Aliah Mohd Hidzir, Nurwahida Yaakub, Shafinar Ismail, Nurbaity Sabri, Hanifiyah Yuliatul Hijriah, Himmatul Kholidah

The Indonesian Capital Market Review

Personal bankruptcy is a pertinent topic to discuss due to the surge in personal bankruptcy cases around the world and it is an important indicator of household financial problems nationally. However, only few comprehensive reviews have been conducted to date. Hence, this study provides a bibliometric review of 210 studies on personal bankruptcy authored by 496 scholars. Bibliographical data were extracted from the Scopus database and analyzed it using the Bibliometrix-R software. Based on the citation analysis metrics, we revealed the most influential articles, journals, authors, and institutions. Using the network and conceptual structure analysis, we identified three underlying research …

Towards Efficient Privacy-Preserving Deep Learning: He-Friendly Structures, Flexible Pruning, He-Efficient Architectures, And Secure Transformer Token Drop, Yifei Cai

Electrical & Computer Engineering Theses & Dissertations

Deep learning (DL) has become a powerful tool for solving complex problems, but developing DL models typically requires vast datasets, high computational resources, and expert knowledge—barriers that limit accessibility. Machine Learning as a Service (MLaaS) addresses this challenge by allowing resource-rich providers to deliver pre-trained DL models as services. However, privacy concerns arise: clients hesitate to share sensitive data, while providers protect their proprietary models. To address this, privacy-preserving MLaaS integrates cryptographic techniques into DL computations, as seen in frameworks like Cryptonets, SecureML, GAZELLE, CrypTFlow2, Cheetah, and BOLT. Among them, Homomorphic Encryption (HE) enables computation on encrypted data but remains …

Connecting Children With Artists Through A Children's Art History Book, Katie Meyer

Theses

This project is a children’s art history book that is set in an art museum. The goal of the book is to help children connect with Contemporary artists and their art. A museum setting is utilized to introduce children to museums and as an appropriate environment for viewing art. The theme of the exhibit that will be presented in the book is titled the “Innovators Exhibit.” This exhibit features six Contemporary artists from different art styles/mediums. The artists come from diverse backgrounds to expose children to a variety of cultures. Thought provoking questions will also be asked throughout the book …

Ms4 Swmpp 2025, National Technology & Engineering Solutions Of Sandia, Llc (Ntess) And Department Of Energy (Doe)

Municipal Separate Storm Sewer System (MS4) Permit

Stormwater discharges from Sandia National Laboratories/New Mexico (SNL/NM) are eligible for coverage under the National Pollutant Discharge Elimination System (NPDES) Municipal Separate Storm Sewer System (MS4) Permit. This Stormwater Management Plan (SWMP) was prepared by National Technology and Engineering Solutions of Sandia (NTESS) for the Department of Energy (DOE) National Nuclear Security Administration (NNSA) Sandia Field Office (SFO), owner of SNL/NM, located in Albuquerque, NM.

Vocabulary Learning Strategies Among Saudi Efl Military Cadets: Patterns And Preferences, Fahad Aldosari

Language, Literacy, and Sociocultural Studies ETDs

This study investigates the vocabulary learning strategies (VLSs) of 126 Saudi military EFL cadets, an underexplored group in second language acquisition research. Using an explanatory sequential mixed-methods design, a questionnaire identified the most and least used strategies, followed by interviews with 10 participants for deeper insights. Findings show cadets frequently use bilingual dictionaries, vocabulary lists, and group work, while cognitive strategies like written repetition and note-taking are underutilized. No significant differences in VLS use were found between Level 1 and Level 2 cadets, suggesting stable strategy preferences. Additionally, emerging strategies such as gamified learning and collaborative storytelling indicate a shift …

O-Mapl: Offline Multi-Agent Preference Learning, The Viet Bui, Tien Mai, Hong Thanh Nguyen

Research Collection School Of Computing and Information Systems

Inferring reward functions from demonstrations is a key challenge in reinforcement learning (RL), particularly in multi-agent RL (MARL). The large joint state-action spaces and intricate inter-agent interactions in MARL make inferring the joint reward function especially challenging. While prior studies in single-agent settings have explored ways to recover reward functions and expert policies from human preference feedback, such studies in MARL remain limited. Existing methods typically combine two separate stages, supervised reward learning, and standard MARL algorithms, leading to unstable training processes. In this work, we exploit the inherent connection between reward functions and Q functions in cooperative MARL to …

Sparse-To-Dense: A Free Lunch For Lossless Acceleration Of Video Understanding In Llms, Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu

Research Collection School Of Computing and Information Systems

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually very long. We observe that during decoding, the attention scores of most tokens in Video-LLMs tend to be sparse and concentrated, with only certain tokens requiring comprehensive full attention. Based on this insight, we introduce Sparse-to-Dense (StD), a novel decoding strategy that integrates two distinct modules: one leveraging sparse top-K attention and the other employing dense full attention. These modules collaborate to accelerate Video-LLMs without loss. …

Breaking The Reasoning Barrier: A Survey On Llm Complex Reasoning Through The Lens Of Self-Evolution, Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolution, and self-evolution. Data evolution explores methods to generate higher-quality reasoning training data. Model evolution focuses on training strategies to boost reasoning capabilities. Self-evolution research autonomous system evolution via iterating cycles of data and model evolution. We further discuss the scaling law of self-evolution and analyze representative O1-like works through this lens. By summarizing advanced methods and outlining future directions, this …

Simulating Before Planning: Constructing Intrinsic User World Model For User-Tailored Dialogue Policy Planning, Tao He, Lizi Liao, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in dialogue policy planning have focused on optimizing system agent policies to achieve predefined goals, emphasizing strategy design, trajectory acquisition, and training efficiency. However, these approaches often overlook the critical role of user characteristics, which are essential in real-world scenarios like conversational search and recommendation, where interactions must adapt to individual user traits such as personality, preferences, and goals. To address this gap, we conduct a comprehensive study using task-specific user personas to evaluate dialogue policy planning under diverse user behaviors. Our analysis, based on these user profiles, reveals significant shortcomings in existing approaches, underscoring the necessity for …

Rustmap: Towards Project-Scale C-To-Rust Migration Via Program Analysis And Llm, Xuemeng Cai, Jiakun Liu, Xiping Huang, Yijun Yu, Haitao Wu, Chunmiao Li, Bo Wang, Imam Nur Bani Yusuf, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Migrating existing C programs into Rust is increasingly desired, as Rust offers superior memory safety while maintaining C’s high performance. Existing automated translation tools, such as C2Rust, may rely too much on syntactic, template-based translation and generate unsafe Rust code that is hard for human developers to read, maintain, or even compile. More semantic-aware translation that produces safer, idiomatic, and runnable Rust code is much needed. This paper introduces a novel dependency-guided and large language model (LLM)-based C-to-Rust translation approach, RustMap, based on three key ideas: (1) Utilize LLM’s capabilities to produce idiomatic Rust code from given small pieces of …

Retrieval Augmented Generation For Dynamic Graph Modeling, Yuxia Wu, Lizi Liao, Yuan Fang

Research Collection School Of Computing and Information Systems

Modeling dynamic graphs, such as those found in social networks, recommendation systems, and e-commerce platforms, is crucial for capturing evolving relationships and delivering relevant insights over time. Traditional approaches primarily rely on graph neural networks with temporal components or sequence generation models, which often focus narrowly on the historical context of target nodes. This limitation restricts the ability to adapt to new and emerging patterns in dynamic graphs. To address this challenge, we propose a novel framework, Retrieval-Augmented Generation for Dy namic Graph modeling (RAG4DyG ), which enhances dynamic graph predictions by incorporating contextually and temporally relevant examples from broader …

Robust Relevance Feedback For Interactive Known-Item Video Search, Zhixin Ma, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Known-item search (KIS) involves only a single search target, making relevance feedback-typically a powerful technique for efficiently identifying multiple positive examples to infer user intent-inapplicable. PicHunter addresses this issue by asking users to select the top-k most similar examples to the unique search target from a displayed set. Under ideal conditions, when the user's perception aligns closely with the machine's perception of similarity, consistent and precise judgments can elevate the target to the top position within a few iterations. However, in practical scenarios, expecting users to provide consistent judgments is often unrealistic, especially when the underlying embedding features used for …

Under The Legal Lens: Navigating Psychological Safety And Conflict For Black Women In Legal Support Roles, Chanel M. Bradden

Electronic Theses and Dissertations

The intersectional challenges of Black women in legal support roles are an overlooked phenomenon in organizational research. Despite diversity efforts in the legal profession, Black women face challenges due to gender, race, and professional status that impact their career advancement, as well as their mental and psychological well-being. As a result of experiencing the effects of racialized workplace dynamics and destructive leadership behaviors, Black women in legal support roles find resilience through self-protection strategies while working through the effects of intersecting forms of oppression in legal workspaces. This study addressed the lack of knowledge of the lived experiences of Black …

Dynamic Few-Shot Prompting For Clinical Note Section Classification Using Lightweight, Open-Source Large Language Models, Kurt Miller, Steven Bedrick, Qiuhao Lu, Andrew Wen, William Hersh, Kirk Roberts, Hongfang Liu

Faculty, Staff and Student Publications

Objective: Unlocking clinical information embedded in clinical notes has been hindered to a significant degree by domain-specific and context-sensitive language. Identification of note sections and structural document elements has been shown to improve information extraction and dependent downstream clinical natural language processing (NLP) tasks and applications. This study investigates the viability of a dynamic example selection prompting method to section classification using lightweight, open-source large language models (LLMs) as a practical solution for real-world healthcare clinical NLP systems.

Materials and methods: We develop a dynamic few-shot prompting approach to classifying sections where section samples are first embedded using a transformer-based …