Related papers: Code Swarm: A Code Generation Tool Based on the Au…
Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs)…
Code LLMs have become extremely popular recently for modeling source code across a variety of tasks, such as generation, translation, and summarization. However, transformer-based models are limited in their capabilities to reason through…
Increasing demands in software industry and scarcity of software engineers motivates researchers and practitioners to automate the process of software generation and configuration. Large scale automatic software generation and configuration…
Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from code, and auto-completing methods. Yet, state-of-the-art…
Writing software exploits is an important practice for offensive security analysts to investigate and prevent attacks. In particular, shellcodes are especially time-consuming and a technical challenge, as they are written in assembly…
In recent years, large pre-trained Language Models of Code (CodeLMs) have shown promising results on various software engineering tasks. One such task is automatic code update recommendation, which transforms outdated code snippets into…
With the growing popularity of Large Language Models (LLMs) in software engineers' daily practices, it is important to ensure that the code generated by these tools is not only functionally correct but also free of vulnerabilities. Although…
Collective decision-making is a key function of autonomous robot swarms, enabling them to reach a consensus on actions based on environmental features. Existing strategies require the participation of all robots in the decision-making…
To reduce the complexity of software, Developers manually simplify program (known as developer-induced program simplification in this paper) to reduce its code size yet preserving its functionality but manual simplification is…
Ensuring correctness is crucial for code generation. Formal verification offers a definitive assurance of correctness, but demands substantial human effort in proof construction and hence raises a pressing need for automation. The primary…
Frequent cyber-attacks have elevated WebShell exploitation and defense to a critical research focus within network security. However, there remains a significant shortage of publicly available, well-categorized malicious-code datasets…
Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating…
Code generation by Llama 3.1 models, such as Meta's Llama 3.1 405B, represents a significant advancement in the field of artificial intelligence, particularly in natural language processing and programming automation. This paper explores…
The use of low- and no-code modeling tools is today an established way in practice to give non-programmers an opportunity to master their digital challenges independently, using the means of model-driven software development. However, the…
Generative AI enables rapid ``vibe coding," where natural language prompts yield working software systems. While this lowers barriers to software creation, it also collapses the boundary between prototypes and engineered software, leading…
Template-based code generation (TBCG) is a synthesis technique that produces code from high-level specifications, called templates. TBCG is a popular technique in model-driven engineering (MDE) given that they both emphasize abstraction and…
Program synthesis is the task of automatically generating a program consistent with a given specification. A natural way to specify programs is to provide examples of desired input-output behavior, and many current program synthesis…
Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O…
With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human languages to programming languages. In this survey paper,…
Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the security of AI-generated code using Large Language Models (LLMs) remains…