Search Results (93)

Tyrosinase is a pivotal therapeutic target for hyperpigmentation disorders, yet current inhibitors frequently exhibit limited potency and suboptimal safety. Here, we employed structure-based virtual screening of an FDA-approved drug library against a refined human tyrosinase homology model, identifying methotrexate and selinexor as potent anti-melanogenic candidates. Both compounds markedly suppressed cellular tyrosinase activity and melanin synthesis (IC₅₀ < 1 µM) in MNT-1 melanoma cells. Mechanistically, they orchestrate a multi-pronged downregulation of microphthalmia-associated transcription factor (MITF) by attenuating cAMP/PKA/CREB signaling, promoting β-catenin degradation, and accelerating MITF proteolysis via AKT/ERK activation. Additionally, they bolster the intracellular antioxidant defense system. These findings unveil a sophisticated regulatory network and suggest that with strict control of systemic exposure through optimized topical formulations, these FDA-approved agents could be further investigated as potential localized treatments for pigmentary disorders. Full article

Clinical reasoning over 3D CT scans is inherently compositional, requiring the integration of anatomical measurement, pathology assessment, spatial comparison, and clinical interpretation. We introduce MedToolica, a finetuning-free, role-based agentic framework for quantitative 3D abdominal CT reasoning that decomposes complex queries into structured sub-tasks coordinated through specialized expert tools. Empirical evaluation across quantitative reasoning benchmarks demonstrates that MedToolica is particularly effective in organ-centric measurement tasks when supported by reliable expert tools, achieving strong quantitative agreement (e.g., $CCC=0.99$ for organ HU estimation versus $0.46$ for finetuned baselines) and notable gains on multi-step visual reasoning tasks. In contrast, lesion-oriented tasks remain constrained by upstream tool limitations, indicating that reasoning sophistication alone cannot compensate for unreliable perception. Furthermore, we observe that the capability of the core language model substantially influences orchestration quality: smaller LLM orchestrators exhibit reduced overall accuracy due to higher execution failure rates ($25\%$ vs. $79\%$) and increased susceptibility to hallucination ($43\%$ vs. $2\%$). Collectively, these findings identify expert tool reliability and orchestration capability as critical determinants of performance in compositional medical AI and highlight both the promise and current limitations of finetuning-free agentic reasoning for quantitative 3D CT analysis. Full article

Future Internet applications such as intelligent transportation, immersive services, and edge-assisted artificial intelligence require latency-sensitive service provisioning at the network edge. In containerized mobile edge computing (MEC), service orchestration is not only a task-offloading problem, but also a task–container–image constrained decision problem: an offloaded task can be executed only when the required runtime container is active, and a newly activated container must be supported by a locally cached service image. This dependency couples task placement, runtime container caching, and persistent image caching under limited RAM and ROM resources. To address this challenge, this paper proposes HAM-MADDPG, a dependency-aware hierarchical action-masked multi-agent reinforcement learning algorithm for joint task offloading and image–container caching in containerized MEC networks. HAM-MADDPG decomposes the monolithic orchestration decision into three causally ordered policy layers: task offloading, runtime container caching, and persistent image caching. Each layer learns a structured subproblem conditioned on upstream realized decisions, while dynamic action masking and feasibility-aware action realization guide the learned policies toward executable decisions satisfying task–container and container–image constraints. Extensive simulations under dynamic service demands and heterogeneous edge resources show that HAM-MADDPG achieves more stable convergence than non-hierarchical reinforcement learning baselines and reduces long-term system latency by approximately 14–25% compared with representative heuristic and flat DRL baselines. Full article

Modelling constitutes a disciplined transformation process through which heterogeneous, unstructured evidence is translated into structured representations that support reasoning and decision-making. The integration of generative artificial intelligence into such processes introduces new possibilities for automation, yet risks undermining methodological rigour, traceability, and human accountability. This paper proposes a methodology-grounded multi-agent architecture for constructing structured business ecosystem maps from unstructured document collections. The architecture decomposes the modelling lifecycle into specialised agent functions covering boundary specification, source discovery, document analysis, semantic extraction, and controlled model editing, addressing four of the five methodology stages while leaving automated completeness verification outside the current scope. A central orchestrator coordinates agents while enforcing ontological constraints derived from a formal modelling methodology. All proposed modifications are staged for human review before execution, and each map element maintains explicit provenance links to source material. To evaluate the reliability and correctness of generative modelling pipelines, a hybrid evaluation framework integrates operational metrics, semantic assessment using an LLM-based judge, and human agreement validation. Empirical evaluation across 34 generative models and 4382 experimental runs characterises capabilities across modelling tasks. In a controlled single-document extraction task, text-based extraction achieves a mean semantic match score of 0.947, whereas interaction extraction scores 0.431 and visual diagram interpretation scores 0.470, identifying relational reasoning and multimodal interpretation as principal bottlenecks. Model performance varies across agent roles, with task-aligned model selection associated with larger performance changes than hyperparameter tuning; the architecture’s causal contribution is not isolated, and comparison against monolithic or ablated baselines remains future work. Full article

The proliferation of digital financial news offers unprecedented opportunities for automated analysis of market-moving events. This paper presents a framework for event-based sentiment analysis of financial news that leverages Large Language Models (LLMs). The approach brings together three complementary ideas: Retrieval-Augmented Generation (RAG) for contextual enhancement, Graph Neural Networks (GNNs) for modeling relationships between events, and a multi-agent ensemble for orchestrated reasoning. The methodology targets well-known difficulties in financial text processing, including domain-specific terminology, implicit event detection, and temporal reasoning, and it combines transformer-based event extraction with sentiment classification enhanced by external knowledge retrieval. We evaluate six model configurations on an aggregated corpus of 14,851 financial news samples. On the event-detection task, every configuration reaches a weighted F1-score of 100%; we show that this is a ceiling effect produced by a binary event/no-event formulation over a highly imbalanced dataset rather than evidence of a difficult problem being solved, and we discuss what it implies for how such systems should be evaluated. On three-way sentiment classification, the strongest configuration—the multi-agent ensemble—reaches 87.4% accuracy, narrowly ahead of a RoBERTa (Robustly Optimized BERT Pretraining Approach) baseline at 87.2%; however, because the gaps reported between models are small and we did not run significance testing, we report them as indicative rather than definitive. The GNN component is described as part of the proposed design, but it has not yet been validated experimentally, and we state this limitation explicitly. The framework produces interpretable, structured outputs suited to downstream use in algorithmic trading, risk assessment, and investment decision support, and the paper contributes a reusable financial NLP pipeline together with a candid account of where the current evidence is, and is not, convincing. Full article

The rapid development of the Industrial Internet of Things (IIoT) generates massive heterogeneous sensor data, complicating data cleaning and normalization. Existing algorithmcentric methods often treat quality issues in isolation and lack unified governance. This paper proposes a governance-centered framework for multi-source industrial sensor data. We introduce an Intelligent Catalog as the semantic governance layer to standardize metadata and achieve semantic alignment before numerical processing. Building upon this, an AI Agent-driven mechanism dynamically orchestrates cleaning and normalization strategies based on real-time data status and heterogeneous features. This framework modularly integrates classical algorithms (e.g., PCA, KPCA, LSTM) without model dependency. Experimental results on public IIoT datasets demonstrate that our framework significantly outperforms baseline methods in normalization consistency, noise robustness, and stability across heterogeneous data. By shifting from an algorithm-centered to a governance-centered paradigm, this approach provides a scalable and adaptive solution for complex industrial sensor data management. Full article

Deploying Large Language Models (LLMs) in collaborative multi-agent settings represents a promising frontier for complex AI problem-solving, yet the field lacks systematic mechanisms to manage the inherent coordination overhead and resource contention that arise at scale. Existing LLM-based Multi-Agent System (MAS) frameworks predominantly adopt sequential or loosely coupled execution models, which fail to exploit the parallelism potential of modern computing environments and limit overall system throughput. To bridge this gap, this paper presents DynTaskMAS, a framework that redefines task orchestration in LLM-based MASs through a dynamic task graph abstraction. Rather than treating tasks as static pipelines, DynTaskMAS continuously models task interdependencies at runtime, enabling opportunistic parallel execution while preserving logical correctness. The architecture integrates four synergistic components: a runtime task decomposition module that captures evolving dependencies among subtasks; a scheduling engine that dispatches ready tasks to available agents without centralized bottlenecks; a context propagation layer that maintains shared semantic state across concurrently executing agents; and a self-tuning workflow controller that adapts execution priorities based on observed system load. Together, these components address a core tension in LLM-based MAS design, balancing agent autonomy with coordinated efficiency. Evaluations across tasks of varying complexity confirm that DynTaskMAS delivers substantial gains in execution efficiency (21.3–33.0% reduction), resource utilization (from 65% to 88%), and agent scalability (3.47× throughput with 16 concurrent agents) compared to sequential baselines. This work offers a generalizable architectural blueprint for next-generation LLM-based Multi-Agent Systems operating under real-world dynamic and resource-constrained conditions. Full article

The massive heterogeneous data streams and stringent low-latency requirements in the Industrial Internet of Things (IIoT) pose new challenges for edge network resource management. This paper addresses the joint optimization problem of Service Function Chain (SFC) orchestration and resource allocation in edge gateway-assisted IIoT networks, formulated as a mixed-integer nonlinear programming (MINLP) model to minimize end-to-end latency and energy consumption while satisfying quality-of-service (QoS) constraints. To tackle this NP-hard problem and the challenges of partial observability in distributed environments, we propose the SFC Orchestration and Resource Allocation-based Multi-Agent Proximal Policy Optimization (SORA-MAPPO) algorithm. The algorithm adopts a centralized training with decentralized execution (CTDE) paradigm with an intelligent agent cooperation mechanism. Simulation results validate the effectiveness of the proposed scheme in complex IIoT scenarios. Full article

Power grids are becoming more connected with 5G networks and edge-computing systems, including in civilian, emergency, and military critical-infrastructure environments. Because of this, optimization is no longer only a power-system problem or only a communication-network problem. It now involves energy, network, and computing resources simultaneously. This review focuses on grid telemetry supported by 5G network slicing and edge analytics. In this setting, data from PMUs, SCADA systems, IEDs, and AMI devices are used not only for monitoring but also for supporting state estimation, anomaly detection, and control decisions. The article reviews several AI-based optimization methods. These include learning-to-optimize, reinforcement learning, safe learning, multi-agent learning, federated learning, AirComp, graph-based models, and hybrid approaches. The review discusses these methods in relation to smart energy control, network slicing, military-resilient power and communication service, edge orchestration, and end-to-end system evaluation. Particular attention is given to tail latency, jitter, reliability, runtime, compute limits, and SLA violations, since average metrics alone are insufficient for critical grid operations. The review also proposes a practical roadmap from pilot co-simulation to edge-first analytics, slicing assurance, security hardening, and continuous monitoring, aiming to support reliable, sustainable and military-relevant smart-grid operation. Full article

Critical infrastructures are increasingly Internet-connected cyber–physical systems whose recovery after cyber incidents must satisfy safety, timing, regulatory, and interdependency constraints. Yet, the use of large language models (LLMs) for generating recovery plans remains fragmented across cybersecurity, industrial control, digital twins, and AI assurance research. This review synthesizes that emerging field through a structured critical survey of studies on LLMs in incident response, OT/ICS resilience, and cyber–physical recovery, with a focused perspective on grounding, trust, and assurance mechanisms relevant to recovery-plan generation. It develops an architecture-centric taxonomy spanning prompt-only assistants, retrieval-augmented copilots, graph-aware planners, multi-agent systems, and hybrid verification/simulation pipelines; maps realistic applications across energy, water, manufacturing, transportation, healthcare, and telecommunications; and organizes limitations into technical, security, governance, and human-factor categories. Based on this synthesis, the paper proposes the Grounded Recovery Planning Stack as a reference architecture and outlines a staged roadmap from human-in-the-loop copilots to bounded orchestration. The main conclusion is that near-term value lies in grounded, auditable, compliance-aware copilots, whereas autonomous recovery execution remains premature without stronger validation, state-aware grounding, sector-specific benchmarks, and formal safeguards. Full article

This article presents a sustainable, system-level approach to personalized practical learning in digital education environments based on tightly integrating formal models of practical tasks and artificial intelligence technologies. The authors resolve the limitations of current methods in e-learning personalization—such as lack of scalability, insufficient adaptability, and unreliable automation—by introducing an improved application which uses Belief–Desire–Intention (BDI) multi-agent system with adaptive orchestration and domain-specific language of formal practical task specification in the framework of an AI assistant, based on service-oriented architecture (SOA). The proposed approach provides automation for the entire lifecycle of practical tasks, encompassing generation, parameterization, and deployment of a virtual run-time environment and result verification for correctness, reproducibility, and academic integrity. Experimental tests demonstrate that combining a large language model (LLM) with dynamic verification significantly outperforms traditional purely generative approaches in terms of reliability, scalability, and reduction in instructor workload, as well as contributing to more effective task performance by students in practice-oriented learning scenarios. The study concludes that the synergistic integration of formal control mechanisms and AI-driven adaptivity offers a robust foundation for building sustainable smart environments for digital learning ecosystems. Full article

Embedding large language model (LLM) coordinators in production electronic systems, connected vehicles, multi-robot fabrics, IoT control loops, telecommunications orchestration, demands a pre-delivery filter stage that preserves ethical guarantees under adversarial influence at deployment scale. We present a constitutional governance layer that filters compiled influence policies before they reach a heterogeneous population of grounded LLM agents whose hybrid decision model combines a game-theoretic base probability with an LLM-evaluated narrative shift attenuated by per-agent resistance. Four experiments on a Barabási–Albert scale-free network of 30 agents powered by Llama-3.3-70B-Instruct show that the filter holds an Ethical Cooperation Score (ECS) of $0.176$ (multi-seed mean $0.163$, 95% confidence interval (CI) $[0.150,0.174]$) against an unconstrained baseline of $\mathrm{ECS}=0$, enforced by a hard integrity gate ($1.000$ vs. $0.000$). We surface an autonomy paradox in which unconstrained agents resist manipulation more forcefully ($0.856$ vs. $0.728$) yet collapse to $\mathrm{ECS}=0$, establishing that system-level integrity cannot be delegated to agent-level defence. The advantage is monotonic in resistance ($+0.174$ to $+0.183$), seed-stable (Cliff’s $\delta =1.0$, complete separation), topology- and backbone-invariant across five contemporary LLMs, robust to alternative ECS formulations, and reproduces at N = 100. Against constitutional artificial intelligence (CAI) critique-revise and LlamaGuard-style safety-classifier baselines, the framework matches the integrity floor and adds a measurable margin on the secondary risk surface (burst timing, composite manipulation risk). The filter runs at 0.78 μs/call ($\approx 1.3\times {10}^6$ decisions/s/core), supporting always-on deployment as a stateless, model-agnostic component of LLM agent pipelines in adversarially contested electronic systems. Full article

Tool-augmented large language model agents are increasingly proposed for network configuration, but routing protocols differ in the control-plane state each commanded router can observe. This difference creates a specific problem for multi-agent orchestration: agents may coordinate more, yet still fail when correct verification depends on peer- or remote-router evidence. We study this interaction through 350 controlled runs on RIP, OSPF, and BGP tasks implemented with FRRouting and Containerlab, comparing a single-agent baseline with multi-agent orchestration patterns across language models. Protocol-centric trace metrics, including spatial coverage, coordination tax, and cross-router verification gap, are combined with intent-property scores and model-balanced bootstrap analysis. The results show that observability explains performance more clearly than orchestration patterns: multi-agent templates trail the baseline on local RIP feedback, show only small and uncertain gains on single-area OSPF troubleshooting, and remain near zero on stricter multi-area OSPF and BGP tasks where peer-side verification gaps are often complete. The main contribution is therefore a protocol-centered account of when agentic orchestration helps, when it adds coordination cost, and why current architectures face a cross-router verification ceiling. Full article

Synthetic Aperture Radar (SAR) image interpretation in dynamic scenarios faces critical challenges, including sluggish multi-agent scheduling responses, sub-optimal task-resource matching, and low full-pipeline collaborative efficiency. To address these issues, this paper proposes an autonomous SAR image interpretation algorithm based on a Mission Control Point (MCP)-driven centralized multi-agent collaborative scheduling framework. To address inefficient task–resource matching, a multi-source orchestration model integrating agent states, task characteristics, and environmental dynamics is developed for optimized initial allocation. To mitigate information fragmentation and improve collaboration efficiency across the pipeline, an MCP-based centralized architecture is proposed to achieve unified scheduling and global optimization of multi-stage agents. Furthermore, to enhance adaptability in dynamic environments, a verification-driven adaptive policy continuous optimization mechanism is introduced, allowing the scheduling policy to continuously adapt. Experiments have been conducted on the SARCAP public dataset, and the proposed method achieved a task–agent matching accuracy of 97.98%, an average scheduling latency of 66.1 ms, and a collaborative interpretation speed of 17.9 fps. Compared with MAPPO and conventional centralized scheduling, scheduling efficiency was improved by 12.3% and 18.7%, respectively. Ablation studies further indicate that both the MCP centralized scheduling mechanism and the multi-source information orchestration module significantly contributed to performance, ensuring high accuracy and robustness. Full article

Smart contract auditing remains challenging because vulnerabilities often emerge only under complex execution conditions, cross-transaction interactions, and environment-dependent assumptions. Existing analysis techniques, including static analysis, symbolic execution, fuzzing, and recent LLM-assisted approaches, each provide useful but incomplete coverage, and monolithic auditing pipelines often struggle to balance search breadth, reproducibility, and reporting reliability. This paper presents SEMA, a self-evolving multi-agent auditing framework for smart contracts that formulates auditing as a resource-bounded discovery of concrete counterexamples under replay-certified reporting semantics. SEMA combines heterogeneous specialized agents, an orchestrator, a shared artifact-centric knowledge base, and a replay-based referee. During auditing, agents generate and consume reusable artifacts, such as candidate invariants, refuted hypotheses, transaction templates, and coverage cues, allowing the shared search state to evolve across rounds without modifying the analyzers themselves. To ensure reporting reliability, findings are accepted only when the referee can replay the candidate scenario under a pinned execution configuration and confirm violation of an executable security property. We further evaluate SEMA on an annotated smart contract benchmark under a fixed 300 s budget per contract. The full system achieves 0.9469 instance recall, 0.9441 success rate, and 0.9445 macro-average category recall on the retained executable subset, outperforming both symbolic-only and fuzzing-only baselines, as well as multi-agent ablations that disable dynamic knowledge evolution or cross-agent artifact reuse. Full article