Aug 2026· 2026 2nd International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)· pp. 1-7· 0 citations· 48 references
Abstract
Large Language Models (LLMs) have demonstrated impressive performance in natural language understanding and generation tasks. However, standalone LLMs are susceptible to hallucinations and are unable to retrieve real-time or domain-specific knowledge. Retrieval-Augmented Generation (RAG) addresses these limitations by grounding generated responses in relevant external knowledge sources. This paper proposes an intelligent RAG-based system that incorporates multi-tool integration and smart workflow orchestration. The proposed system dynamically retrieves relevant documents from vector databases and invokes external tools, such as calculators and application programming interfaces (APIs), to generate accurate, reliable, and context-specific responses. The system will be implemented using embedding models, vector databases, LLMs, and tool-invocation mechanisms.
Discover the immense potential of Generative AI and Large Language Models (LLMs) with this comprehensive guide. Learn to overcome LLM limitations, such as contextual memory constraints, prompt size issues, real-time data gaps, and occasional ‘hallucinations’. Follow practical examples to personalize and launch your Lla...
The growth of document collections has made manual analysis inefficient in contexts that require synthesis and traceability. This work proposes a framework for orchestrating pipelines in the context of Intelligent Process Automation (IPA), focused on processing unstructured data. The solution integrates OCR, NLP, machi...
Arthur C. e Silva, Robson Costa, Daniel Coutinho et al.· Brazilian Symposium on Datab...· 0 citations
Enterprise customer-support agents increasingly rely on Large Language Models (LLMs) to execute bounded, tool-using workflows. We study this problem through the lens of Skill LLMs: specialized executors that operate within a selected skill context and must complete a narrow, stateful workflow under policy and tool cons...
Md Tahmid Rahman Laskar, Gundeep Singh, Xue-Yong Fu et al.· 0 citations
This paper provides a principled definition for the FOL-autoformalization task by distinguishing Ontology Extraction from Logical Translation and identifies open challenges in benchmarking, semantic evaluation, ontology-aware methods, and end-to-end applications.
Andrea Brunello, Cristian Curaba, Luca Geatti et al.· 1 citation
Natural Language Processing systems are increasingly built as configurable pipelines combining heterogeneous components, including data sources, task specifications, linguistic preprocessing, representation methods, learning models, training settings, evaluation protocols, explainability requirements, and deployment co...
Kamal Walji, Allae Erraissi, Abdelali Zakrani et al.· International journal of adv...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
