Agent System Research Articles

Analysis of Accelerating Ideation Process with Large Language Model

Abstract. Large Language Models (LLMs) have rapidly advanced, demonstrating near-human intelligence in language comprehension, problem-solving, and autonomous decision-making, which can be leveraged in scientific discovery. Previous research of LLM for science often focuses on experiment execution part and the first stage of research, i.e., idea generation with large language models is lack of research. This paper fills this gap by surveying the use of LLM-based agent systems in research idea generation. This research first proposes three stages in research idea generation pipeline, pre-ideation (knowledge preparation), ideation (generation and iteration), post-ideation (evaluation), and provide detailed summary in different methods in each stage, then it summarizes different metrics and angles of evaluating generated research ideas, finally it discusses limitations and ethical concerns of existing works and suggest potential solutions and future directions. These results aim to provide a solid foundation for future research in improving LLM-based ideation systems and fostering responsible AI usage in scientific discovery.

Comparison of Multi-Agent Platform Usability for Industrial-Grade Applications

Modern systems often employ decentralised and distributed approaches. This can be attributed, among others, to the increasing complexity of system processes, which go beyond the capabilities of singular components. Additionally, with the growth in demand for system automation and high-level coordination, solutions belonging to the decentralised Artificial Intelligence and collaborative decision-making are often applied. It can be observed that these concerns fall within the domain of multi-agent systems. However, even though MAS concepts emerged more than 40 years ago, despite their obvious advantages and continuous efforts of the scientific community, agents remain rarely used in industrial-grade applications. In this context, the goal of this contribution is to analyse the reasons for the lack of adoption of agent solutions in the real world. During the analysis, all pertinent aspects of the modern software development life cycle are examined and compared to what is currently available in the agent system domain. Specifically, the study focuses on identifying gaps that are often overlooked when it comes to scientific applications of MAS, but are critical in terms of potential for large-scale system development in practice.

Development of Hybrid Implantable Local Release Systems Based on PLGA Nanoparticles with Applications in Bone Diseases.

The current strategy for treating osteomyelitis includes surgical procedures for complete debridement of the formed biofilm and necrotic tissues, systemic and oral antibiotic therapy, and the clinical use of cements and three-dimensional scaffolds as bone defect fillers and delivery systems for therapeutic agents. The aim of our research was to formulate a low-cost hybrid nanoparticulate biomaterial using poly(lactic-co-glycolic acid) (PLGA), in which we incorporated the therapeutic agent (ciprofloxacin), and to deposit this material on titanium plates using the matrix-assisted pulsed laser evaporation (MAPLE) technique. The deposited material demonstrated antibacterial properties, with all analyzed samples inhibiting the growth of tested bacterial strains, confirming the release of active substances from the investigated biocomposite. The poly(lactic-co-glycolic acid)-ciprofloxacin (PLGA-CIP) nanoparticle scaffolds displayed a prolonged local sustained release profile over a period of 45 days, which shows great promise in bone infections. Furthermore, the burst release ensures a highly efficient concentration, followed by a constant sustained release which allows the drug to remain in the implant-adjacent area for an extended time period.

Emergent behaviors of buckling-driven elasto-active structures

Active systems of self-propelled agents, e.g., birds, fish, and bacteria, can organize their collective motion into myriad autonomous behaviors. Ubiquitous in nature and across length scales, such phenomena are also amenable to artificial settings, e.g., where brainless self-propelled robots orchestrate their movements into spatial-temporal patterns via the application of external cues or when confined within flexible boundaries. Like their natural counterparts, these approaches typically require many units to initiate collective motion, so controlling the ensuing dynamics is challenging. Here, we demonstrate a simple mechanism that leverages nonlinear elasticity to tame near-diffusive motile particles in forming structures capable of directed motion and other emergent behaviors. Our elasto-active system comprises two centimeter-sized self-propelled microbots connected with elastic beams. These microbots exert forces that suffice to buckle the beam and set the structure in motion. We first rationalize the physics of the interaction between the beam and the microbots. Then we use reduced-order models to predict the interactions of our elasto-active structures with boundaries, e.g., walls and constrictions, and demonstrate how they can exhibit remarkable emergent behaviors such as maze navigation. These findings demonstrate that allowing and understanding changes in body morphology can enhance the capabilities of active matter systems and enable the design of robotic materials capable of space exploration, adaptation, and complex interactions with their surrounding environment.

Use of modified human hemangioma tissue cultures and human umbilical vein endothelial cell cultures to gain mechanistic insights into imiquimod treatment for infantile hemangioma.

Infantile hemangiomas (IH) are a common entity encountered by dermatologists, otolaryngologists, and other surgeons. Oral propranolol is a mainstay of treatment for IH and is well-tolerated, though propranolol-refractory IH and other drug-related adverse events are documented and can limit its usage. There are few in vitro testing systems for putative treatment agents. To address this, we modified a tissue culture system for human hemangioma treatment testing to evaluate the treatment impact of the immune modifier, imiquimod. Human umbilical vein endothelial cells (HUVEC) and hemangioma cultures were treated with several concentrations of imiquimod followed by MTT assays, reporter gene assays, PCR, ELISA, and Western blotting for IL-8, VEGF, Cyclin D1, and IFNα and immunohistochemistry for Cyclin D1 and Ki-67. HUVEC showed acute decreases in IL-8, VEGF, and Cyclin D1 promoter activity and increases in IFNα mRNA after imiquimod treatment. Hemangioma samples showed no change in Ki-67 or Cyclin D1 staining after treatment with imiquimod after 27 d, with significantly increased IL-8 and VEGF. From this preliminary analysis, we discerned that hemangioma tissues can be grown in tissue culture and used for drug treatment studies. We also conclude acute and chronic modulation of cell cycle, angiogenesis factors, and immunostimulatory conditions may be associated with imiquimod mechanisms of action in hemangioma involution.

A Systematic Review of Mesenchymal Stem Cell-Derived Extracellular Vesicles: A Potential Treatment for Glioblastoma

Background: Glioblastoma (GBM) is an extremely aggressive brain tumor that has few available treatment options and a dismal prognosis. Recent research has highlighted the potential of extracellular vesicles (MSC-EVs) produced from mesenchymal stem cells as a potential treatment approach for GBM. MSC-EVs, including exosomes, microvesicles, and apoptotic bodies, perform a significant function in cellular communication and have shown promise in mediating anti-tumor effects. Purpose: This systematic literature review aims to consolidate current findings on the therapeutic potential of MSC-EVs in GBM treatment. Methods: A systematic search was conducted across major medical databases (PubMed, Web of Science, and Scopus) up to September 2024 to identify studies investigating the use of MSC-derived EVs in GBM therapy. Keywords included “extracellular vesicles”, “mesenchymal stem cells”, “targeted therapies”, “outcomes”, “adverse events”, “glioblastoma”, and “exosomes”. Inclusion criteria were studies published in English involving GBM models both in vivo and in vitro and those reporting on therapeutic outcomes of MSC-EVs. Data were extracted and analyzed based on EV characteristics, mechanisms of action, and therapeutic efficacy. Results: The review identified several key studies demonstrating the anti-tumor effects of MSC-EVs in GBM models. A total of three studies were included, focusing on studies conducted between 2021 and 2023. The review included three studies that collectively enrolled a total of 18 patients. These studies were distributed across two years, with two trials published in 2023 (66.7%) and one in 2021 (33.3%). The mean age of the participants ranged from 37 to 57 years. In terms of gender distribution, males were the predominant group in all studies. Prior to receiving MSC-EV therapy, all patients had undergone standard treatments for GBM, including surgery, chemotherapy (CT), and, in some cases, radiation therapy (RT). In all three studies, the targeted treatment involved the administration of herpes simplex virus thymidine kinase (HSVtk) gene therapy delivered to the tumor site, then 14 days of ganciclovir treatment. Outcomes across the studies indicated varying levels of efficacy for the MSC-EV-based therapy. The larger 2023 study reported fewer encouraging outcomes, with a median PFS of 11.0 months (95% CI: 8.3–13.7) and a median OS of 16.0 months (95% CI: 14.3–17.7). Adverse effects were reported in only one of the studies, the 2021 trial, where patients experienced mild-to-moderate side effects, including fever, headache, and cerebrospinal fluid leukocytosis. A total of 11 studies on preclinical trials, using in vitro and in vivo models, were included, covering publications from 2010 to 2024. The studies utilized MSCs as delivery systems for various therapeutic agents (interleukin 12, interleukin 7, doxorubicin, paclitaxel), reflecting the versatility of these cells in targeted cancer therapies. Conclusions: MSC-derived EVs represent a promising therapeutic approach for GBM, offering multiple mechanisms to inhibit tumor growth and enhance treatment efficacy. Their ability to deliver bioactive molecules and modulate the tumor microenvironment underscores their potential as a novel, cell-free therapeutic strategy. Future studies should optimize EV production and delivery methods and fully understand their long-term effects in clinical settings to harness their therapeutic potential in GBM treatment.

Development and validation of a predictive scoring system for hypoglycaemic agents for optimal control of blood glucose during glucocorticoid therapy.

Glucocorticoid (GC) treatments are often used. There is limited information on the prediction of hyperglycaemia after GC administration. This study aimed to identify the risk factors for hyperglycaemia after glucocorticoid (GC) administration and the need for hypoglycaemic agents to correct it and to develop and validate a novel scoring system for predicting GC-induced hyperglycaemia. In a development set, 508 adults receiving prednisolone (PSL) for the first time were divided into two groups based on treatment with or without hypoglycaemic agents. Clinical and laboratory parameters were compared, and risk factors were identified using logistic regression analysis after performing univariate analyses between the two groups. A point-addition scoring system with several categories and coefficients for each risk factor was constructed to predict the need for hypoglycaemic agents. The scoring system was then applied and validated on two validation sets: A and B. Older age, higher glycated haemoglobin percentage, body mass index and initial PSL dosage were identified as risk factors. The sensitivity, specificity and accuracy of the scoring system were 70.6%, 81.9% and 77.1% in the development set; 75.8%, 78.4% and 77.4% in validation set A; and 79.4%, 73.9% and 75.3% in validation set B respectively. By fitting the total score in the development set and the probability of hyperglycaemia to a logistic curve, a figure was created to show the probability of GC-induced hyperglycaemia in patients scheduled to receive GC. This scoring system is a novel, valid and reliable tool for predicting GC-induced hyperglycaemia and the need for hypoglycaemic agents to correct it.

Fabrication and Properties of in Situ Cross‐Linked Supramolecular Gel Based on Host‐Guest Interaction

AbstractWater‐cut control is critical to efficient reservoir development. In this investigation, a host‐guest inclusion polymer gels system with self‐assembly features was constructed stemming from the host‐guest recognition mechanism. Subsequently, the elements affecting polymer viscosity were discussed. Eventually, the injectivity and plugging performance of the host‐guest inclusion system were measured by core displacement tests. The results indicated that the optimum synthesis temperature of the host polymer and guest polymer were 30 °C and 40 °C, separately, and the optimum total monomer content should be 20 wt%. The polymer system had excellent thickening properties and shearing resistance resulting from host‐guest inclusion interaction and physical hydrophobic association. Meanwhile, it had better plugging performance than host polymer or guest polymer alone. This profile control agent system provides a novel method for settling deep profile control in oilfields.

Computer Simulation and Simulation of Mechanical and Electrical Equipment based on Artificial Intelligence Algorithms

The computer in mechanical and electrical equipment can now detect equipment faults through simulation thanks to the advancement of artificial intelligence (AI) technology, which makes it convenient to monitor mechanical and electrical equipment. This paper begins with a quick introduction to Agent and the Agent system, explains how Agent is applied in the current context, then analyzes the hierarchical fault diagnostic model, identifies its flaws, and suggests improvement techniques. To increase the model’s accuracy and speed of operation, the contract net model and D-S (Dempster-Shafer) evidence theory are then incorporated. Finally, simulation experiments are used to confirm the accuracy and consistency of this model. According to the experimental findings, this optimization model runs at a pace that is noticeably faster than that of other models when subjected to the same workload, demonstrating the model’s efficacy. Models 1, 2, and 3 are put side by side to demonstrate how clearly multi-task processing may cut down on the model’s running time. In the second experiment, samples of mechanical and electrical equipment defect data are taken from two groups. The results of the comparative experiments demonstrate that the optimized model in this work can be reliable up to a maximum of 0.91 and a minimum of 0.63. It is demonstrated that the model in this work is rational by the fact that among the four types of fault prediction, the optimized model’s reliability is significantly greater than the traditional model’s. The research described in this publication therefore has some reference value for computer simulation of electromechanical equipment.

The Human‐Data Interaction Driven by Data Reuse

ABSTRACTThe data‐intensive research paradigm is sweeping through the scientific community, and new interaction challenges for interacting with data have emerged. Data reuse emerges as a critical driver of human‐data interaction, positioning data repositories at the forefront as the optimal solution for facilitating this process. This study adopts a diary study methodology to analyze the data repository‐supported human‐data interaction behaviors driven. The findings reveal that human‐data interaction extends beyond mere engagement with data, encapsulating elements of human‐computer interaction, engagement with literature, interactions with agent systems, and interpersonal communication.

Preparation and Performance Evaluation of Self-Degrading Temporary Plugging Agent for Well Workover of Fractured Reservoir

Abstract The temporary plugging technology is considered an important technology in the well workover process of oil and gas reservoirs. Gel is a frequently employed temporary plugging agent in oilfields; however, it has drawbacks, including poor cross-linking strength, unpredictable gelation duration, and considerable reservoir damage after application. To solve these issues, this study seeks to create a gel-based temporary plugging agent system that will improve the dependability and efficiency of oilfield development. In the study, acrylamide, hydrophobic monomers, initiators, crosslinkers, inorganic components, and scale inhibitors were used to formulate the temporary plugging agent. To close underground channels, the prepared plugging agent is injected into the underground and gels at high temperatures. In this study, the elastic modulus of the gel was investigated with a HAAKE rheometer, and the core flooding test was carried out to evaluate the plugging efficiency of the gel. Meanwhile, the visual code method was used to observe the formation time of the temporary plugging agent, and the self-degradation performance of the temporary plugging agent was studied. Hydrophobic monomers and inorganic materials significantly enhance the mechanical properties of the temporary plugging agent after forming the glue. The elastic modulus after crosslinking can reach about 450 Pa, and the maximum pressure of plugging can reach 2.4 MPa. The crosslinking time can be controlled within 30 minutes to 10 hours by adding the inhibitor. The crosslinking agent used in the system is ester organic matter, which can be hydrolyzed at high temperatures to achieve self-degradation performance, so that the degradation rate of the temporary plugging agent can reach 90% within 7 days after forming the glue. This temporary plugging agent has high strength, a controlled crosslinking time, and good self-degradation performance as compared to the typical gel-type temporary plugging agent. These qualities are crucial for reservoir protection and well workover.

RETRACTION: Internet of Agents System for Age and Gender Classification Using Grasshopper Optimization With Deep Convolution Neural Networks

<scp>RETRACTION</scp>: Internet of Agents System for Age and Gender Classification Using Grasshopper Optimization With Deep Convolution Neural Networks

The future image as a component of political subjective space: testing the conceptual model

The image of the future of youth is described in this paper and its relationship with the subjective space of politics is identified. The article provides a brief analysis of research on the image of the future within the framework of social and political sciences, describes the main theoretical approaches to analyzing the future image of youth. The authors give their own conceptual definition of the future image as a component of the political subjective space, a set of symbolic, ideological and cultural meanings that determine the orientation and behavior of various political actors. The authors as a methodology use focus group interviews, online questionnaires of youth representatives in order to verify the conceptual model of the study. The dynamic nature of the future image as a part of political subjective space is determined by a system of institutions, agents and factors of socialization. Five key components have been identified in the structure of the future image: content, value, emotions, activity and technology. Four projection levels of the future image are defined: personal, group, projection at the level of the macro community and global. The study indicates the predominance of personal projection in the respondents' ideas about the future. Despite the presence of worries and fears for their personal future, young people are generally confident in their own future and believe that the Russian state will continue to play an important role as a world power. An important characteristic of the future image is the subjectivity of its bearer, the degree of activity or proactivity and the willingness to take responsibility for their own future and the future of their families, local community, region, country, and the world. Locus control, that is, a subjective assessment of the factors (personal efforts or external circumstances) on which the future depends, according to the study, is associated with the degree of confidence in the future, the formation of a positive future image. The predominance of civic identity in the hierarchy of identities is also revealed. Young people feel responsible for the future of their country. At the moment, Russian civic identity has a positive impact on the future image of young people. It is significant that among students studying in the Luhansk People's Republic, the level of concern about the future is higher, the level of civil identity is lower, which indicates that the task of forming civil identity should be prioritized in the new regions of the Russian Federation.

Elaboration and investigation of formulated polymer composites as some potential anticorrosion coatings for brass surface in 3.5% NaCl solution: theoretical approaches

ABSTRACT Polymer composite derivatives [(TGEMM/MDA/0%, TGEMM/MDA/6%, TGP/MDA/0%, and TGP/MDA/6%)] were elaborated through using tetraglycidyl ether of methyl-α-D-mannopyranoside (TGEMM) and 2,3,4,5-tetraglycidyloxy pentanal (TGP) as matrices, methylene dianiline (MDA) as curing agent and glass system (1-x) (2Bi2O3 - B2O3) - x BaO (with x = 0% and 6%) as filler. Different composites prepared were investigated as some potential anticorrosive protection coatings for brass electrode in sodium chloride medium (3.5% NaCl). Polymer composite coatings were characterized using FTIR spectroscopy, SEM/EDS, EFM, PDP, and EIS techniques. The anticorrosive protection efficiencies increase with increasing charge incorporated in composites, in the following order: TGP/MDA/0% < TGEMM/MDA/0% < TGP/MDA/6% < TGEMM/MDA/6% and the later achieving a maximum of 90.67% (EFM), 95.45% (PDP), and 97.86% (EIS), respectively. SEM/EDS characterization suggests a smooth surface in the presence of composite derivatives, which is more significant in the presence of TGEMM/MDA/6%. DFT calculations and MD simulations confirm the data obtained by experimental study and offer insights into its structural properties.

The Value of Small Samples to Groups and Teams Research: Accumulating Knowledge across Philosophies of Science

The large increase in the average sample size of team studies published in premier management journals over the past decade is concerning. A strict focus on large samples suppresses the study of many teams, particularly less prominent ones; for example, teams in small or medium-sized enterprises, teams in unique contexts, teams containing underrepresented minorities, and teams adopting new technologies. It also impedes our collective understanding of teams by devaluing work relying on philosophies of science that do not prioritize large samples. Large samples allow positivists to establish relationships between constructs. Yet, contextualized, rich data from as few as just one team can help constructivists uncover lived experiences or could be studied by critical realists to identify mechanisms underlying social systems of active agents. In this paper, we review how these three philosophies of science view sample size, addressing how and when small samples are beneficial. Importantly, research from all three traditions is necessary to build an in-depth, practical understanding of teams. We also describe five specific ways small sample research can contribute to team science and lay out four general recommendations for assessing the value of sample size in team research. Throughout, we maintain that scientific progress is collective and pluralistic. A sole reliance on large samples threatens this goal.

In Vitro Bond Strength of Dentin Treated with Sodium Hypochlorite: Effects of Antioxidant Solutions.

This systematic review aims to evaluate whether the application of antioxidant solutions can enhance the bond strength of resin-based materials to sodium hypochlorite (NaOCl)-treated dentin. This study follows the PICOT strategy: population (sodium hypochlorite-treated dentin), intervention (application of antioxidants), control (distilled water), outcome (bond strength), and type of studies (in vitro studies). The systematic review and meta-analysis were conducted following PRISMA guidelines. Electronic databases were searched for in vitro studies evaluating the effects of antioxidants on bond strength to sodium hypochlorite-treated dentin. Two independent reviewers screened articles, extracted data, and assessed risk of bias. Meta-analyses were performed using a random-effects model to compare standardized mean differences in bond strength between antioxidant pretreatment and control groups. Inclusion criteria consisted of in vitro studies that examined the bond strength of resin-based materials to NaOCl-treated dentin with antioxidant application, while exclusion criteria included studies with incomplete data, those not using a control group, or those that did not directly measure bond strength. From 3041 initial records, 29 studies were included in the qualitative analysis and 25 in the meta-analysis. Ascorbic acid, sodium ascorbate, grape seed extract, green tea, and rosmarinic acid significantly improved bond strength to sodium hypochlorite-treated dentin (p < 0.05). The effectiveness of grape seed extract varied with adhesive system type. Hesperidin, p-toluene sulfonic acid, and sodium thiosulfate did not significantly improve bond strength. Most studies had a high risk of bias. This suggests that the conclusions drawn from these studies should be interpreted with caution, and further research with more robust methodologies may be needed to confirm the findings. In conclusion, this systematic review implies that certain antioxidants can improve bond strength to sodium hypochlorite-treated dentin, with efficacy depending on the specific agent and adhesive system used. Further standardized studies are needed to optimize protocols and confirm these findings.

THERMODYNAMICS OF CARBOTHERMAL REDUCTION PROCESS COPPER SLAG

The article analyses the thermodynamic laws of processing iron-based compounds contained in copper production slag using the method of carbothermic recovery. Evaluation of the probable direction of carbothermic reactions occurring between oxidized compounds and carbon in the slag was carried out by changing the thermodynamic values of the system. In the thermodynamic scientific justification of the physic-chemical processes occurring in the carbothermic recovery of metal oxides in slag, the change of Gibbs energy of the system with temperature increases and the estimation of equilibrium constants of chemical reactions based on Gibbs energy and the method of determining the slowest (limiting) chemical process among them were used. The Microsoft Excel program was used to determine the thermodynamic values of the chemical reactions occurring in the slag and reducing agent system and to compile their Ellingham graphs.

Change in sexual and reproductive health knowledge among young women using the conversational agent “Nthabi” in Lesotho: a clinical trial

BackgroundYoung women worldwide face problems like unwanted pregnancy and sexually transmitted infections. Providing sexual and reproductive health education to young women in low- and middle-income countries is a priority. It is unknown if using digital health interventions to deliver health education is effective in resource-constrained settings.MethodsWe conducted an interventional trial among young women in the low–middle-income country of Lesotho to test the impact of the conversational agent system (“Nthabi”) designed to deliver sexual and reproductive health information on either a smartphone or tablet for up to 6 weeks. We measured participant’s knowledge before and after the discussion of family planning, folic acid use, and healthy eating. The main outcome measure was a change in knowledge among participants in these three topic areas. The number of correct pre- and post-test responses was compared using generalized linear models that directly estimated the proportions and percentages of correct responses.ResultsWe recruited 172 young women (mean age 22.5 years, 91% unmarried, 69% completed high school, 23% unemployed, 66% students) to use Nthabi on a mobile phone (11.6%) or loaned tablet device (88.4%). The mean number of interactions with Nthabi was 8.6. Family planning was chosen to be discussed by 82 of the 172 participants (52.2%), and of those, 49 (31.2%) completed the content on this topic, and 26 (16.6) completed the post-test. For the 11 questions about family planning, the total percent of correct responses increased from 85.5% (796 total responses) on the pre-test to 89.9% (320 responses) on the post-test (p = 0.0233). Folic acid use was chosen to be discussed by 74 (47.1%) of 172 participants, and of those, 27 (17.7%) completed the content on this topic, and all 27 (17.7%) completed the post-test. For the 5 questions about folic acid use, the total percent of correct responses was 45.3% (181 total responses) on the pre-test and 71.6% (111 responses) on the post-test (p < 0.0001).ConclusionsThe Nthabi conversational agent system increased knowledge of family planning methods and folic acid use among young women in Lesotho. Digital health interventions like Nthabi have the potential to offer new ways to deliver reproductive health information.Trial registrationClinicalTrials.gov registration April 20, 2020; ID: NCT04354168.

Adaptive distributed tracking control for Markov jump multiagent systems with a non-strict leader

This paper investigates the leader-following mean square distributed tracking control problem (DTCP) for a Markov jump multiagent systems (MJMASs) with the general linear dynamical model over an undirected graph. The non-strict control input of the leader is non-zero, unknown, and unavailable to any followers. First, the jump characteristics of the system for the single agent is modeled by a continuous Markov chain. Second, in order to address the leader–follower mean square DTCP, the distributed mode-dependent static controller and the fully distributed mode-dependent adaptive controller are designed for all followers based on the information from the agents’ neighbors and itself, respectively. Then, to further analyze the stability of the MJMASs, two categories of decomposed related Lyapunov functions are constructed using Lyapunov stability theory. The sufficient conditions for the existence of the distributed controller are obtained by derivation. Finally, two simulation cases are presented to verify the validity and feasibility of the proposed strategies.

Bioinspired Polyoxomolybdate Nanoclusters Peroxidase‐Mimicking Nanozyme for Dual‐Mode Detection of Methotrexate in Real Samples

ABSTRACTMethotrexate (MTX) is a chemotherapy agent and immune system suppressant that is widely used to treat a variety of malignant and nonmalignant diseases. Due to some drawbacks of the existing methods for the determination of MTX in aquatic and real samples, we prepared a new, simple, and selective dual‐mode fluorometric and electrochemical approach based on peroxidase‐mimic [Mo36] polyoxomolybdate nanoclusters (POMo) for sensing MTX. A turn‐on–off fluorometric approach for the detection of MTX was developed, which was based on the inhibition of the emission intensity of the terephthalic acid (TA)‐H2O2 system upon the addition of MTX to the reaction solution. The electrocatalytic performance of the obtained POMo was studied after making a carbon paste electrode (CPE) utilizing cyclic voltammetry and amperometry analysis. Under the optimum condition, good linearity was observed between the quenched emission intensity of the system and MTX dosage in the range of 0.5–250 μM with a limit of detection (LOD) of 0.91 μM. The electrochemical method illustrated a much better response with an extensive linear range of 0.01–475 μM and a lower LOD (1.61 nM). Analytical recoveries and RSD% values were, respectively, in the range of 87.72%–110% and 0.33%–1.32% for the fluorometric system and 96%–106% and 0.77%–1.02% for the electrochemical platform. Finally, the selectivity of the sensor was evaluated against various common interfering species, and the results indicated satisfactory selectivity of the POMo dual‐mode system towards MTX.