相关论文: A Baseline Model for Software Effort Estimation

According to a study of The Standish Group International, 44% of software projects cost more and last longer than expected. More accurate the effort estimation is; the better the enterprise gets organized and the more the software project…

Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in…

Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and…

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Reducing cost and time required to build high quality software is a major goal for software developers. Building tools and techniques that can help achieve such a goal is the chief aim for Automated Software Engineering (ASE) researchers.…

The rapid advancement of software development practices has introduced challenges in ensuring quality and efficiency across the software engineering (SE) lifecycle. As SE systems grow in complexity, traditional approaches often fail to…

Structural equation modeling (SEM) and path analysis have long been central tools for studying complex causal relationships in the social and behavioral sciences, yet their reliance on parametric assumptions can lead to biased inference…

Structural equation models (SEMs) are widely used in sciences, ranging from economics to psychology, to uncover causal relationships underlying a complex system under consideration and estimate structural parameters of interest. We study…

Large Language Models (LLMs) are revolutionizing Software Engineering (SE) by introducing innovative methods for tasks such as collecting requirements, designing software, generating code, and creating test cases, among others. This article…

Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based…

In this paper, we propose improvements in how estimation bias, e.g., the tendency towards under-estimating the effort, is measured. The proposed approach emphasizes the need to know what the estimates are meant to represent, i.e., the type…

With the rapid development of LLM-based agents, there is a growing trend to incorporate agent-specific data into the pre-training stage of LLMs, aiming to better align LLMs with real-world autonomous task execution. However, current…

AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable. Tools that can automate aspects of modeling practice must complement human expertise,…

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…

LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…

Continual fine-tuning of large language models (LLMs) suffers from catastrophic forgetting. Rehearsal-based methods mitigate this problem by retaining a small set of old data. Nevertheless, they still suffer inevitable performance loss.…

Many critical applications, from autonomous scientific discovery to personalized medicine, demand systems that can both strategically acquire the most informative data and instantaneously perform inference based upon it. While amortized…

The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite the promise and some decent results, the existing AutoEval…

While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…