LLMs and RAG have very good capabilities to reason about context and semantic mapping. However, existing AI solutions have been limited in the sense that they can only generate text-based responses, without executing any commands in a safe manner. This research paper proposes LLM-RAG Automation: Intelligent Function Execution and Secure System Orchestration, an intelligent automation solution that bridges the gap between natural language processing and autonomous executable workflows. LLM-RAG maps the intent of the users to pre-validated capabilities using PostgreSQL and pgvector. In order to make sure that the solution is secure, the multi-agent engine (which is made up of planning, execution, validation, and security components) performs risk assessment before executing tasks in a sandboxed environment. Instead of relying on scripts or generating executable code through LLMs, the proposed solution leverages pre-validated executable functions to make sure that the task execution is always reliable. Through empirical studies, we demonstrate that retrieval of the function minimizes execution latency and prevents any kind of unsafe command orchestration through multi-step workflows.
Cowkur, A., Nambiar, R., Nambiar, R. & Sukanya, V. (2026). Ragexe - Llm-Rag Automation: Intelligent Function Execution and Secure System Orchestration. International Journal of Innovations & Research Analysis, 06(03(I)), 01–15. https://doi.org/10.62823/IJIRA/06.3(I).9202
- P. Lewis, E. Perez, A. Piktus, et al., “Retrieval- Augmented Generation for Knowledge-Intensive NLP Tasks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2020.
- V. Karpukhin, B. Oguz, S. Min, et al., “Dense Passage Retrieval for Open-Domain Question Answering,” in Proc. EMNLP, 2020.
- T. B. Brown, B. Mann, N. Ryder, et al., “Language Models are Few-Shot Learners,” arXiv preprint arXiv:2005.14165, 2020.
- S. Yao, J. Zhao, D. Yu, et al., “ReAct: Synergizing Reasoning and Acting in Language Models,” in Proc. ICLR, 2023.
- T. Schick, J. Dwivedi-Yu, R. Dessì, et al., “Toolformer: Language Models Can Teach Themselves to Use Tools,” arXiv preprint arXiv:2302.04761, 2023.
- Y. Gao, Y. Xiong, X. Gao, et al., “Retrieval-Augmented Generation for Large Language Models: A Survey,” arXiv preprint arXiv:2312.10997, 2023.
- A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi, “Self- RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection,” in Proc. ICLR, 2024.
- J. Johnson, M. Douze, and H. Jégou, “Billion-Scale Similarity Search with GPUs,” IEEE Trans. Big Data, 2019.
- N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” in Proc. EMNLP-IJCNLP, 2019.
- O. Khattab, A. Singhvi, P. Maheshwari, et al., “DSPy: Compiling Declarative Language Model Calls into Self- Improving Pipelines,” in Proc. ICLR, 2024.
- A. Vaswani, N. Shazeer, N. Parmar, et al., “Attention Is All You Need,” in Proc. NeurIPS, 2017.
- L. Ouyang, J. Wu, X. Jiang, et al., “Training Language Models to Follow Instructions with Human Feedback,” in Proc. NeurIPS, 2022.
- S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “RAGAS: Automated Evaluation of Retrieval Augmented Generation,” in Proc. EACL, 2024.
- J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019. doi: 10.18653/v1/N19-1423.
- C. Raffel, N. Shazeer, A. Roberts, et al., “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” J. Mach. Learn. Res., vol. 21, no. 140, pp. 1–67, 2020.
- J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. H. Chi, Q. V. Le, and D. Zhou, “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” in Proc. 36th Conference on Neural Information Processing Systems (NeurIPS), 2022.
