This research work proposes a LLM-powered chatbot aimed at supporting students and educators in databases and information systems in higher education. The chatbot leverages the capabilities of LLM to facilitate interactive learning, offering real-time assistance on various database-related topics, including query formulation, data modeling, and system design. The chatbot incorporates advanced pre-processing techniques such as text cleaning, tokenization, stop words removal, and stemming/lemmatization to prepare user inputs for effective analysis. Feature extraction methods such as Bag-of-Words (BOW), n-grams, and Improved Term Frequency-Inverse Document Frequency (ITF-IDF) convert textual data into numerical forms, enhancing model understanding and accuracy. Additionally, deep learning algorithms, Hybrid Convolutional Long Short-Term Memory (HCLSTM) networks, are integrated to enhance the chatbot's ability to generate contextually relevant responses. Optimization is achieved through the Improved Artificial Bee Colony (IABC) algorithm, which fine-tunes the chatbot's parameters for superior performance. Through an interactive user interface, the chatbot provides personalized learning experiences, helping students grasp complex concepts in databases and information systems. Initial testing indicates the system's effectiveness in delivering insightful, tailored responses, making it a valuable tool for enhancing the learning process in higher education.

Conventional signature-based defenses no longer protect the heterogeneous, large-scale infrastructures that the Internet of Things (IoT) now constitutes. Large language models (LLMs) and agentic artificial intelligence (AI)—systems that autonomously perceive, reason, plan, and act—open a path to self-defending IoT ecosystems, but the integrating literature remains fragmented. Within the IEEE Xplore, ACM Digital Library, and MDPI literature, this survey is, to the best of our knowledge, among the first systematic reviews of agentic AI and LLM-driven approaches for autonomous IoT cybersecurity. Following a PRISMA 2020 protocol, we analyze 153 peer-reviewed studies published between 2020 and 2026 in IEEE Xplore, the ACM Digital Library, and MDPI journals. We organize the corpus along a four-pillar taxonomy: agent architecture (single- vs. multi-agent), reasoning strategy (chain-of-thought, ReAct, plan-and-solve, tool use), action scope (detection, response, threat hunting, vulnerability discovery, deception), and deployment topology (edge, fog, cloud). We synthesize four flagship application domains, consolidate datasets and benchmarks, and analyze open challenges including hallucination, prompt-injection robustness, explainability, privacy, latency, and governance. A 2026 research roadmap identifies federated agentic learning, verifiable autonomous reasoning, trustworthy multi-agent collaboration, and resource-hardened edge agents as high-priority directions. A companion reproducibility kit—prompt templates, reference single- and multi-agent loops, and an Edge-IIoTset-style evaluation harness, released as illustrative scaffolding rather than a validated framework—is released publicly and archived on Zenodo (DOI 10.5281/zenodo.20726552).

Portland cement production accounts for roughly 8% of anthropogenic CO2 emissions, driving interest in low-carbon geopolymer binders. One-part (“just-add-water”) geopolymers, which replace hazardous liquid activators with a dry, pre-blended solid activator, are especially suited to field deployment where handling safety and logistics are decisive. However, their formulation space is combinatorially vast, and trial-and-error development cannot efficiently navigate it. This paper reviews one-part geopolymer science, presents a new comparative and interpretable ML analysis of a published 80-mixture one-part fly-ash/GGBS geopolymer dataset from twelve studies, and proposes an AI-assisted design framework. The ML demonstration targets 28-day compressive strength only. Under leave-one-source-out (LOSO) cross-validation—the appropriate test for a literature-pooled dataset—gradient-boosted trees achieved R2 = 0.61, well above a linear baseline (0.36), suggesting that non-linear structure transfers across studies; a random split gives a higher but less reliable R2 = 0.90 on only 16 test mixtures. Because fly-ash and GGBS contents are near-perfectly anti-correlated (r=−0.99), we model the precursor axis as a single slag-fraction descriptor; SHAP then identifies this precursor balance and the activator’s Na2O dosage as the dominant, mechanistically coherent strength levers. Demonstrated for strength, the framework offers a transferable route toward multifunctional low-carbon binders for protective and infrastructure applications.

Conventional signature-based defenses no longer protect the heterogeneous, large-scale infrastructures that the Internet of Things (IoT) now constitutes. Large language models (LLMs) and agentic artificial intelligence (AI)—systems that autonomously perceive, reason, plan, and act—open a path to self-defending IoT ecosystems, but the integrating literature remains fragmented. Within the IEEE Xplore, ACM Digital Library, and MDPI literature, this survey is, to the best of our knowledge, among the first systematic reviews of agentic AI and LLM-driven approaches for autonomous IoT cybersecurity. Following a PRISMA 2020 protocol, we analyze 153 peer-reviewed studies published between 2020 and 2026 in IEEE Xplore, the ACM Digital Library, and MDPI journals. We organize the corpus along a four-pillar taxonomy: agent architecture (single- vs. multi-agent), reasoning strategy (chain-of-thought, ReAct, plan-and-solve, tool use), action scope (detection, response, threat hunting, vulnerability discovery, deception), and deployment topology (edge, fog, cloud). We synthesize four flagship application domains, consolidate datasets and benchmarks, and analyze open challenges including hallucination, prompt-injection robustness, explainability, privacy, latency, and governance. A 2026 research roadmap identifies federated agentic learning, verifiable autonomous reasoning, trustworthy multi-agent collaboration, and resource-hardened edge agents as high-priority directions. A companion reproducibility kit — prompt templates, reference single- and multi-agent loops, and an Edge-IIoTset-style evaluation harness — is released at https://github.com/vnageshwaran-de/agentic-iot-security and archived on Zenodo (DOI 10.5281/zenodo.20446651).

Large language models (LLMs) are increasingly deployed as agents that perceive an environment, plan, invoke tools, and act over multi-step trajectories, and a fast-growing literature proposes benchmarks to evaluate them. We argue that the resulting scores are not self-interpreting: what a benchmark number means depends on which capability it measures, how that capability is scored, and where the agent is tested. This article moves beyond the prevailing benchmark catalogue to a validity-centered analysis of agent evaluation, built on a reproducible systematic mapping review under the PRISMA-ScR standard (259 primary studies; 294 in the released living-review corpus). The corpus is a carefully constructed, reproducible mapping sample—not a census of the field: primary-arm records were screened by a single audited automated pass (human double-screening, \(\kappa =0.65\), was applied to the supplementary arm), and broad-map attribute shares are provisional heuristic estimates. The article makes four contributions. An operational definition—the dependent-step test—demarcates autonomous agentic evaluation from static natural-language-processing evaluation and prompt engineering. A meta-taxonomy locates every benchmark in a three-pillar coordinate system of capability (what), scoring paradigm (how), and environment topology (where). An evidence map over the corpus is paired with a purposive, hand-verified, venue-verified landscape matrix of seventeen prominent benchmarks (inter-rater reliability \(\kappa =0.77\)). Finally, a critical analysis shows that data contamination, non-determinism, and execution cost form a structural trilemma: among these seventeen prominent, verified benchmarks, none reports evidence that the three threats are jointly controlled, and none reports a complete standardized run-cost record (0/17). A five-direction roadmap reframes progress as a shift from individual benchmarks toward standardized, reliability-first, cost-aware evaluation infrastructure, supported by an open companion repository.

Portland cement production accounts for roughly 8% of anthropogenic CO₂ emissions, driving interest in low-carbon geopolymer binders. One-part (“just-add-water”) geopolymers, which replace hazardous liquid activators with a dry, pre-blended solid activator, are especially suited to field deployment where handling safety and logistics are decisive. However, their formulation space is combinatorially vast, and trial-and-error development cannot efficiently navigate it. This paper reviews one-part geopolymer science, presents a new comparative and interpretable ML analysis of a published 80-mixture one-part fly-ash/ground granulated blast-furnace slag (GGBS, hereafter slag) geopolymer dataset from twelve studies, and proposes an AI-assisted design framework. The ML demonstration targets 28-day compressive strength only. Under leave-one-source-out (LOSO) cross-validation—the appropriate test for a literature-pooled dataset—gradient-boosted trees achieved R² = 0.61 (RMSE = 15.5 MPa; 95% bootstrap confidence interval on R², 0.44–0.75), well above a linear baseline (0.36), suggesting that non-linear structure transfers across studies; a random split gives a higher but less reliable R² = 0.90 on only 16 test mixtures. Because fly-ash and slag contents are near-perfectly anti-correlated ($r=-0.99$), we model the precursor axis as a single slag fraction descriptor; SHAP then identifies this precursor balance and the activator’s Na₂O dosage as the dominant statistical predictors of strength in this dataset, an ordering consistent with known activation chemistry; causal confirmation of these associations awaits the experimental validation stage of the proposed framework. Demonstrated for strength only, at paste level, the framework offers a transferable route toward multifunctional low-carbon binders for protective and infrastructure applications; the multifunctional extensions are proposed, but not yet demonstrated.