A Metadata-Driven Approach for Testing Self-Organizing Multiagent Systems

Nascimento, Nathalia; Alencar, Paulo; Lucena, Carlos José Pereira de; Cowan, Donald

doi:10.1109/access.2020.3036668

Cited by 10 publications

(5 citation statements)

References 20 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task executor is responsible for performing the tasks outlined in the plan. Within the task executor, a task monitor is necessary to monitor the task's execution status and manage the tasks queued for execution [40,41]. Apart from directly utilizing internal knowledge of FMs to guide the action execution, the task executor can cooperate with other agents or leverage external tools [8,42,43], which expands the capabilities of the agent.…”

Section: Execution Enginementioning

confidence: 99%

Responsible-AI-by-Design: A Pattern Collection for Designing Responsible Artificial Intelligence Systems

Zhu

et al. 2023

IEEE Softw.

View full text Add to dashboard Cite

The release of ChatGPT, Bard, and other large language model (LLM)-based chatbots has drawn huge attention on foundations models worldwide. There is a growing trend that foundation models will serve as the fundamental building blocks for most of the future AI systems. However, incorporating foundation models in AI systems raises significant concerns about responsible AI due to their black box nature and rapidly advancing super-intelligence. Additionally, the foundation model's growing capabilities can eventually absorb the other components of AI systems, introducing the moving boundary and interface evolution challenges in architecture design. To address these challenges, this paper proposes a pattern-oriented responsible-AI-by-design reference architecture for designing foundation model-based AI systems. Specially, the paper first presents an architecture evolution of AI systems in the era of foundation models, from "foundation-model-as-a-connector" to "foundationmodel-as-a-monolithic architecture". The paper then identifies the key design decision points and proposes a pattern-oriented reference architecture to provide reusable responsible-AI-by-design architectural solutions to address the new architecture evolution and responsible AI challenges. The patterns can be embedded as product features of foundation model-based AI systems and can enable organisations to capitalise on the potential of foundation models while minimising associated risks.

show abstract

Section: Execution Enginementioning

confidence: 99%

Responsible-AI-by-Design: A Pattern Collection for Designing Responsible Artificial Intelligence Systems

Zhu

et al. 2023

IEEE Softw.

View full text Add to dashboard Cite

show abstract

“…However, in our opinion, realizing the dream of AGI is still far away, despite of the rapid progress in the LLMs development. The key challenges include; understanding natural intelligence [609], developing adaptable fully autonomous models [610], and being safe and reliable with the understanding of the physical world [611], [612]. • Democratizing AI Democratizing AI [613] is a crucial movement that seeks to make artificial intelligence accessible and inclusive for a wide range of individuals and organizations.…”

Section: B Ethical Considerationsmentioning

confidence: 99%

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

Hadi,

tashi,

Qureshi

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. Large language models (LLMs) are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, and question-answering. This survey paper provides a comprehensive overview of LLMs, including their history, architecture, training methods, applications, and challenges. The paper begins by discussing the fundamental concepts of generative AI and the architecture of generative pre- trained transformers (GPT). It then provides an overview of the history of LLMs, their evolution over time, and the different training methods that have been used to train them. The paper then discusses the wide range of applications of LLMs, including medical, education, finance, and engineering. It also discusses how LLMs are shaping the future of AI and how they can be used to solve real-world problems. The paper then discusses the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, and computational resource requirements. It also highlights techniques for enhancing the robustness and controllability of LLMs, and addressing bias, fairness, and generation quality issues. Finally, the paper concludes by highlighting the future of LLM research and the challenges that need to be addressed in order to make LLMs more reliable and useful. This survey paper is intended to provide researchers, practitioners, and enthusiasts with a comprehensive understanding of LLMs, their evolution, applications, and challenges. By consolidating the state-of-the-art knowledge in the field, this survey serves as a valuable resource for further advancements in the development and utilization of LLMs for a wide range of real-world applications. The GitHub repo for this project is available at https://github.com/anas-zafar/LLM-Survey</p>

show abstract

“…To conduct large-scale tasks, such as inspection of electric power transmission lines, monitoring leaks in gas and oil pipelines, country border patrolling, agriculture, and transportation, the use of multiple robots or agents is more feasible and economical than using a single agent [1], [2]. The control tasks are carried out by multiple agents simultaneously, and new control algorithms must support such framework [3].…”

Section: Introductionmentioning

confidence: 99%

HDP Algorithms for Trajectory Tracking and Formation Control of Multi-Agent Systems

2022

View full text Add to dashboard Cite

A heuristic dynamic programming (HDP) algorithm for trajectory tracking and formation control of multi-agent systems (MAS) is presented in this paper. The selected HDP method allows for an online optimal control design. The multi-agent control problem is formulated as a leader-follower, where it is necessary for followers to maintain the assigned formation, while the leader follows the specified trajectory. Developed QR-Solver and RLS µ -QR-HDP-DLQR algorithms provide a new methodology to obtain the solution of the Hamilton-Jacobi-Bellman (HJB) equation. These proposed solutions are based on QR factorization to decrease the computational cost and avoid issues associated with numerical stability of conventional least squares (LS) method. The algorithms' performances such as convergence, numerical stability, and computational metrics, were experimentally evaluated for two control systems: aerial altitude control (one degree of freedom) and terrestrial robot (two degrees of freedom).

show abstract

A Metadata-Driven Approach for Testing Self-Organizing Multiagent Systems

Cited by 10 publications

References 20 publications

Responsible-AI-by-Design: A Pattern Collection for Designing Responsible Artificial Intelligence Systems

Responsible-AI-by-Design: A Pattern Collection for Designing Responsible Artificial Intelligence Systems

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

HDP Algorithms for Trajectory Tracking and Formation Control of Multi-Agent Systems

Contact Info

Product

Resources

About