The implementation of a hybrid large language model for adaptive cryptographic cyber defense

A Blackwood, J Carrington, S Baryshevsky, G Morrison - 2024 - researchsquare.com
Cybersecurity threats have become increasingly complex and adaptive, requiring dynamic
defense mechanisms that can keep pace with evolving attack vectors. The proposed hybrid …

[HTML][HTML] Agent design pattern catalogue: A collection of architectural patterns for foundation model based agents

Y Liu, SK Lo, Q Lu, L Zhu, D Zhao, X Xu… - Journal of Systems and …, 2025 - Elsevier
Foundation model-enabled generative artificial intelligence facilitates the development and
implementation of agents, which can leverage distinguished reasoning and language …

Prompts are programs too! understanding how developers build software containing prompts

JT Liang, M Lin, N Rao, BA Myers - arxiv preprint arxiv:2409.12447, 2024 - arxiv.org
The introduction of generative pre-trained models, like GPT-4, has introduced a
phenomenon known as prompt engineering, whereby model users repeatedly write and …

A taxonomy of multi-layered runtime guardrails for designing foundation model-based agents: Swiss cheese model for ai safety by design

M Shamsujjoha, Q Lu, D Zhao, L Zhu - arxiv preprint arxiv:2408.02205, 2024 - arxiv.org
Foundation Model (FM) based agents are revolutionizing application development across
various domains. However, their rapidly growing capabilities and autonomy have raised …

Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs

S Kouemo Ngassom, A Moradi Dakhel… - Proceedings of the 1st …, 2024 - dl.acm.org
LLM-based assistants, such as GitHub Copilot and ChatGPT, have the potential to generate
code that fulfills a programming task described in a natural language description, referred to …

Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models

H Li, CP Bezemer, AE Hassan - arxiv preprint arxiv:2410.09012, 2024 - arxiv.org
Foundation models (FMs) such as large language models (LLMs) have significantly
impacted many fields, including software engineering (SE). The interaction between SE and …

From Human-to-Human to Human-to-Bot Conversations in Software Engineering

R Khojah, FG de Oliveira Neto, P Leitner - Proceedings of the 1st ACM …, 2024 - dl.acm.org
Software developers use natural language to interact not only with other humans, but
increasingly also with chatbots. These interactions have different properties and flow …

The ML Supply Chain in the Era of Software 2.0: Lessons Learned from Hugging Face

T Stalnaker, N Wintersgill, O Chaparro… - arxiv preprint arxiv …, 2025 - arxiv.org
The last decade has seen widespread adoption of Machine Learning (ML) components in
software systems. This has occurred in nearly every domain, from natural language …

Software Performance Engineering for Foundation Model-Powered Software (FMware)

H Zhang, S Chang, A Leung, K Thangarajah… - arxiv preprint arxiv …, 2024 - arxiv.org
The rise of Foundation Models (FMs) like Large Language Models (LLMs) is revolutionizing
software development. Despite the impressive prototypes, transforming FMware into …

Watson: A Cognitive Observability Framework for the Reasoning of Foundation Model-Powered Agents

B Rombaut, S Masoumzadeh, K Vasilevski… - arxiv preprint arxiv …, 2024 - arxiv.org
As foundation models (FMs) play an increasingly prominent role in complex software
systems, such as FM-powered agentic software (ie, Agentware), they introduce significant …