863 papers
This paper presents a five-agent generative AI framework that integrates technical, fundamental, and sentiment analysis with anomaly detection and LLM-based reasoning to provide explainable, confidence-aware stock market predictions for Indian equities, achieving 72% directional accuracy and 78% cross-agent consensus.
This paper presents a software framework for anthropocentric dispatch management in Industry 5.0 educational settings that integrates chronotype-aware optimization, adaptive criterion weighting, and intelligent decision support to significantly improve schedule quality, student well-being, and academic outcomes while ensuring fairness across all participant groups.
This paper presents the AgileOps Agentic Framework (AAF), a multi-agent decision-support system that integrates specialized DevOps, SRE, FinOps, and DevSecOps reasoning with explainable, evidence-grounded analysis to help Project Managers interpret fragmented operational telemetry into actionable governance recommendations, validated through controlled scenarios and real-world microservice benchmarks.
This paper introduces SWIFT, a gradient-free, white-box framework that surgically injects sparse steering vectors into the deep critical layers of aligned Large Language Models to restore suppressed capabilities with high auditability, revertibility, and locality, achieving near full-supervised fine-tuning performance in under 10 seconds while modifying less than 1% of parameters.
This paper proposes LADMF, a unified framework that integrates LLM-augmented knowledge graph reasoning with disentangled multimodal fusion and counterfactual causal attention to significantly improve e-commerce conversion prediction accuracy and generate human-readable, faithful explanations.
This paper presents a systematic layer-wise analysis of fine-tuned IndoBERT models for Indonesian misinformation detection, revealing a consistent three-phase representational evolution where critical hoax-related features are formed in intermediate layers and consolidated in upper layers, while highlighting distinct functional roles between [CLS] and mean-pooled representations.
This paper proposes DLMC_Net, a novel deep learning framework combining a customized CNN, an adaptive self-attention module, and Borderline SMOTE to achieve state-of-the-art accuracy (99.92%) in multi-class malware classification using bytecode images, significantly outperforming established baseline models.
This paper introduces a generative agent framework that successfully simulates and quantifies the "Quiet Quitting" phenomenon, revealing that while commitment strategies significantly reduce turnover intentions, their effectiveness is critically moderated by employee personality traits, thereby establishing a computational testbed for precision-targeted crisis management.
This paper demonstrates that natural-language instructions are fragile under hidden operational requirements, revealing that while generic prompting fails to satisfy omitted constraints, performance improves significantly when those constraints are explicitly elicited and executed.
This paper presents a novel LLM-augmented decision intelligence framework that integrates FMEA-based risk quantification with large language model contextual reasoning to achieve statistically significant, high-recall real-time supply chain risk assessment, as validated by both parameterized simulations and extensive empirical testing on the DataCo Smart Supply Chain dataset.