Enhancing Generative AI Reliability via Agentic AI in 6G-Enabled Edge Computing
Bibliographic record
Abstract
Generative artificial intelligence (GenAI), particularly large language models (LLMs), has revolutionized various applications by producing coherent and contextually relevant text. However, despite their advancements, LLMs are prone to hallucinations-instances where the AI generates inaccurate or fabricated information. Retrieval-augmented generation (RAG) has emerged as a technique to enhance GenAI by integrating external knowledge sources beyond the model's training data. While RAG improves factual grounding, it alone cannot fully eliminate hallucinations. To address this limitation, agentic workflows that incorporate external tools such as APIs, search engines, and self-reflective mechanisms offer a promising solution. These workflows enable models to iteratively assess and refine their outputs, thereby reducing errors and enhancing factual accuracy. This paper presents a novel framework that combines agentic workflows with RAG within 6G networks to achieve more reliable generative AI by deploying autonomous agents that reflect on outputs and leverage real-time knowledge from external sources to improve response quality and accuracy. We explore the deployment of these workflows in 6G-enabled edge environments, facilitating scalable, real-time knowledge integration and model refinement. Our framework addresses current limitations in RAG-enhanced services by utilizing 6G edge intelligence for data fusion, dynamic knowledge base updates, and customizable AI service delivery. Through a multi-agent system comprising generator and critic agents, we effectively reduce hallucinations via iterative self-criticism, paving the way for more reliable and accurate generative AI services across diverse applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".