Empowering IoT with Large Language Models: A Survey of Applications, Challenges, and Future Directions
Bibliographic record
Abstract
The integration of Large Language Models (LLMs) with the Internet of Things (IoT) is reshaping intelligent systems, enabling advanced automation, cybersecurity, and natural user interaction in cyber-physical environments. This survey synthesizes recent advances in LLM-IoT integration, highlighting transformative applications, challenges, and emerging solutions. Key applications include intelligent automation, with AutoIoT achieving 94.1%–98.5% accuracy in zero-code orchestration; personalized healthcare, with LLM-HAS reducing false alarms by 8.147%; and cybersecurity via ChatIoT and BARTPredict, the latter with 98% intrusion detection accuracy. Challenges include computational constraints on edge devices, privacy risks in data handling, and hallucinations, with medical LLMs showing up to 15% error rates without fine-tuning. Solutions like federated learning, model compression (reducing memory usage by up to 50%), and hybrid frameworks such as LLMind improve efficiency and privacy. This survey offers a comparative analysis of these approaches, providing insights into their trade-offs. Future research should focus on multimodal LLMs, scalable edge deployments, and trustworthy systems powered by explainable AI. By addressing these issues, LLM-IoT ecosystems can evolve toward resilient, adaptive, and human-centric intelligent systems, enabling more generalizable AI in IoT-driven environments.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.004 | 0.011 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".