MDPI - Publisher of Open Access Journals

30 pages, 438 KB

Open AccessArticle

Multi-Agent RAG Framework for Entity Resolution: Advancing Beyond Single-LLM Approaches with Specialized Agent Coordination

by Aatif Muhammad Althaf, Muzakkiruddin Ahmed Mohammed, Mariofanna Milanova, John Talburt and Mert Can Cakmak

Computers 2025, 14(12), 525; https://doi.org/10.3390/computers14120525 - 1 Dec 2025

Viewed by 1449

Abstract

Entity resolution in real-world datasets remains a persistent challenge, particularly for identifying households and detecting co-residence patterns within noisy and incomplete data. While Large Language Models (LLMs) show promise, monolithic approaches often suffer from limited scalability and interpretability. This study introduces a multi-agent Retrieval-Augmented Generation (RAG) framework that decomposes household entity resolution into coordinated, task-specialized agents implemented using LangGraph. The system includes four agents responsible for direct matching, transitive linkage, household clustering, and residential movement detection, combining rule-based preprocessing with LLM-guided reasoning. Evaluation on synthetic S12PX dataset segments containing 200–300 records demonstrates 94.3% accuracy on name variation matching and a 61% reduction in API calls compared to single-LLM baselines, while maintaining transparent and traceable decision processes. These results indicate that coordinated multi-agent specialization improves efficiency and interpretability, providing a structured and extensible approach for entity resolution in census, healthcare, and other administrative data domains. Full article

(This article belongs to the Special Issue Multimodal Pattern Recognition of Social Signals in HCI (2nd Edition))

► Show Figures

Graphical abstract

11 pages, 518 KB

Open AccessArticle

Occupational Stress in Spanish Police Officers: Validating the Effort-Reward Imbalance Questionnaire

by Lourdes Luceño-Moreno, Beatriz Talavera-Velasco, Marian Jaén-Díaz and Jesús Martín-García

Int. J. Environ. Res. Public Health 2021, 18(4), 1393; https://doi.org/10.3390/ijerph18041393 - 3 Feb 2021

Cited by 7 | Viewed by 3553

Abstract

The Effort-Reward Imbalance Questionnaire (hereinafter, ERIQ) has been largely used worldwide to assess job stress, but it has not yet been applied in Spanish police. The objective of this study was to examine the construct validity and the internal consistency of the ERIQ in police officers. A cross-sectional study was carried out, using a nonprobability sampling (quota). A total of 217 Spanish police officers participated, 192 men (88.47%) and 25 women (11.53%). The mean age was 41 years (SD = 7.51). These police officers completed the ERIQ together with some other questionnaires (DECORE-21, MBI, GHQ and STAI) in order to provide evidence for validity based on the relationships to other constructs. A confirmatory factor analysis was performed and a matrix of correlations with the rest of constructs was created. The results showed an appropriate fit to the original model consisting of three scales. In addition, the scales of the ERIQ presented the expected relationship with the other constructs. The ERIQ is a valid instrument for assessing occupational stress in Spanish police officers and can improve the interventions in this professional group. Full article

(This article belongs to the Section Mental Health)

► Show Figures

Figure 1

14 pages, 7264 KB

Open AccessArticle

Simulation of Cellular Energy Restriction in Quiescence (ERiQ)—A Theoretical Model for Aging

by David Alfego and Andres Kriete

Biology 2017, 6(4), 44; https://doi.org/10.3390/biology6040044 - 12 Dec 2017

Cited by 2 | Viewed by 5557

Abstract

Cellular responses to energy stress involve activation of pro-survival signaling nodes, compensation in regulatory pathways and adaptations in organelle function. Specifically, energy restriction in quiescent cells (ERiQ) through energetic perturbations causes adaptive changes in response to reduced ATP, NAD+ and NADP levels in a regulatory network spanned by AKT, NF-κB, p53 and mTOR. Based on the experimental ERiQ platform, we have constructed a minimalistic theoretical model consisting of feedback motifs that enable investigation of stress-signaling pathways. The computer simulations reveal responses to acute energetic perturbations, promoting cellular survival and recovery to homeostasis. We speculated that the very same stress mechanisms are activated during aging in post-mitotic cells. To test this hypothesis, we modified the model to be deficient in protein damage clearance and demonstrate the formation of energy stress. Contrasting the network’s pro-survival role in acute energetic challenges, conflicting responses in aging disrupt mitochondrial maintenance and contribute to a lockstep progression of decline when chronically activated. The model was analyzed by a local sensitivity analysis with respect to lifespan and makes predictions consistent with inhibitory and gain-of-function experiments in aging. Full article

(This article belongs to the Special Issue Systems Biology of Aging)

► Show Figures

Figure 1

Search Results (3)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (3)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI