Short Courses of ERCEMAPI 2025
Keywords:
Chatbot, Paradigma Multiagente, LangChain, LangGraph, Aplicações Paralelas, Parallel Scalability SuiteSynopsis
This book gathers the tutorials presented at the Regional School of Computing of Ceará, Maranhão and Piauí (ERCEMAPI 2025), addressing topics related to agent-based artificial intelligence and performance analysis of parallel applications. The chapters discuss fundamental concepts and practical aspects of developing computational systems, including agent architectures based on Large Language Models (LLMs) and methods for evaluating scalability and efficiency in parallel computing environments. The first chapter presents the construction of chatbots and intelligent agents using the multi-agent paradigm with the LangChain and LangGraph frameworks, relating concepts from classical agent theory to their implementation in modern applications. The second chapter discusses profiling and scalability analysis of parallel applications, addressing metrics such as speedup, efficiency, and scalability, as well as the use of the Parallel Scalability Suite (PaScal Suite) for collecting and visualizing performance data. The book therefore serves as supporting material for students, researchers, and professionals interested in artificial intelligence and high-performance computing.
Chapters
-
1. AI Agents: Building a Chatbot Using the Multi-Agent Paradigm with LangChain and LangGraph
-
2. Profiling and Visualization of Parallel Application Scalability Using the Parallel Scalability Suite
Downloads
References
Amdahl, G. M. (1967) Validity of the single processor approach to achieving large scale computing capabilities. In Proceedings of the April 18-20, 1967, Spring Joint Computer Conference (pp. 483–485). Association for Computing Machinery.
Hana Derouiche, Haithem Mezni, and Zaki Brahmi. Agentic ai frameworks: Architectures, protocols, and design challenges. arXiv preprint arXiv:2508.10146, 2025.
John L. Gustafson. 1988. Reevaluating Amdahl’s law. Commun. ACM 31, 5 (May 1988), 532–533. DOI: 10.1145/42411.42415
LeiWang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, et al. A survey on large language model based autonomous agents. Frontiers of Computer Science, 2024.
Malik Ghallab, Dana Nau, and Paolo Traverso. Automated Planning: Theory and Practice. Morgan Kaufmann, 1998.
Nóbrega-da-Silva, Anderson, Cunha, Daniel, Silva, Vitor, Araújo Furtunato, Alex Fabiano, and Xavier-de-Souza, Samuel (2019). "PaScal Viewer: A Tool for the Visualization of Parallel Scalability Trends". In: Handbook of Research on Emerging Developments and Applications of High Performance Computing. pp. 250-264. ISBN: 978-981-13-6209-5. DOI: 10.1007/978-3-030-17872-7_15.
Pacheco, P. S. (2011) An introduction to parallel programming. Morgan Kaufmann.
Satyadhar Joshi. Advancing innovation in financial stability: A comprehensive review of ai agent frameworks, challenges and applications. World Journal of Advanced Engineering Technology and Sciences, 14(2):117–126, 2025.
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Wen, and Mike Lewis. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022.
Silva, Vitor, Nóbrega-da-Silva, Anderson, Valderrama Sakuyama, C., Manneback, Pierre, and Xavier-de-Souza, Samuel (2022). "A Minimally Intrusive Approach for Automatic Assessment of Parallel Performance Scalability of Shared-Memory HPC Applications". Electronics, vol. 11, no. 5. DOI: 10.3390/electronics11050689.
Stuart J. Russell and Peter Norvig. Artificial Intelligence: A Modern Approach. Pearson Education, 4th edition, 2020.
