The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack sys...The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack systematic frameworks capable of addressing the contextual and pedagogical nuances required for effective implementation.This paper introduces a novel framework that combines Data-Driven Error-Correcting Output Codes(DECOC),Long Short-Term Memory(LSTM)networks,and Multi-Layer Deep Neural Networks(ML-DNN)to identify optimal emoji placements within computer science course materials.The originality of the proposed system lies in its ability to leverage sentiment analysis techniques and contextual embeddings to align emoji recommendations with both the emotional tone and learning objectives of course content.A meticulously annotated dataset,comprising diverse topics in computer science,was developed to train and validate the model,ensuring its applicability across a wide range of educational contexts.Comprehensive validation demonstrated the system’s superior performance,achieving an accuracy of 92.4%,precision of 90.7%,recall of 89.3%,and an F1-score of 90.0%.Comparative analysis with baselinemodels and relatedworks confirms themodel’s ability tooutperformexisting approaches inbalancing accuracy,relevance,and contextual appropriateness.Beyond its technical advancements,this framework offers practical benefits for educators by providing an Artificial Intelligence-assisted(AI-assisted)tool that facilitates personalized content adaptation based on student sentiment and engagement patterns.By automating the identification of appropriate emoji placements,teachers can enhance digital course materials with minimal effort,improving the clarity of complex concepts and fostering an emotionally supportive learning environment.This paper contributes to the emerging field of AI-enhanced education by addressing critical gaps in personalized content delivery and pedagogical support.Its findings highlight the transformative potential of integrating AI-driven emoji placement systems into educational materials,offering an innovative tool for fostering student engagement and enhancing learning outcomes.The proposed framework establishes a foundation for future advancements in the visual augmentation of educational resources,emphasizing scalability and adaptability for broader applications in e-learning.展开更多
In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new...In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new and successful educational data mining models were analyzed and compared. These models have better performance than traditional models( such as Knowledge Tracing Model) in efficiency,comprehensiveness,ease of use,stability and so on. Then,the neural network algorithm was conducted to explore the feasibility of the application of educational data mining in student management,and the results show that it has enough predictive accuracy and reliability to be put into practice. In the end,the possibility and prospect of the application of educational data mining in teaching management system for university students was assessed.展开更多
This study empirically analyzes the application effect of the integration of medical and educational models in cultivating professional abilities in traditional Chinese medicine rehabilitation techniques.The research ...This study empirically analyzes the application effect of the integration of medical and educational models in cultivating professional abilities in traditional Chinese medicine rehabilitation techniques.The research subjects are 100 students from the Traditional Chinese Medicine Rehabilitation Technology major at Y school.Through questionnaire scores,practical training results,and interview data,this study explores the outcomes of this integrated approach.The findings reveal that students in the experimental group significantly outperform those in the control group in terms of practical operation skills,professional responsibility,and communication and collaboration skills.This research confirms the notable role of the medical-educational integration model in enhancing the professional skills and accomplishments of students majoring in traditional Chinese medicine rehabilitation,providing a scientific basis for vocational education reform and the cultivation of rehabilitation technical talents.展开更多
This paper introduces a new version of the open-source educational software, LESM (Linear Elements Structure Model), developed in MATLAB for structural analysis of one-dimensional models such as frames, trusses, and g...This paper introduces a new version of the open-source educational software, LESM (Linear Elements Structure Model), developed in MATLAB for structural analysis of one-dimensional models such as frames, trusses, and grillages. The updated program includes dynamic analysis, which incorporates inertial and damping effects, time-dependent load conditions, and a transient solver with multiple time integration schemes. The software assumes small displacements and linear-elastic material behavior. The paper briefly explains the theoretical basis for these developments and the reorganization of the source code using Object-Oriented Programming (OOP). The updated Graphical User Interface (GUI) allows interactive use of dynamic analysis features and displays new results such as animations, envelope diagrams of internal forces, phase portraits, and the response of degrees-of-freedom in time and frequency domain. The new version was used in a structural dynamics course, and new assignments were elaborated to improve students’ understanding of the subject.展开更多
This study evaluated the accuracy,completeness,and comprehensibility of responses from mainstream large language models(LLMs)to hepatitis C virus(HCV)-related questions,aiming to assess their performance in addressing...This study evaluated the accuracy,completeness,and comprehensibility of responses from mainstream large language models(LLMs)to hepatitis C virus(HCV)-related questions,aiming to assess their performance in addressing patient queries about disease and lifestyle behaviors.The models selected were ChatGPT-4o,Gemini 2.0 Pro,Claude 3.5 Sonnet,and DeepSeek V3,with 12 questions chosen by two HCV experts from the domains of prevention,diagnosis,and treatment.展开更多
Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interact...Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.展开更多
The collection and annotation of lar ge-scale bird datasets are resource-intensive and time-consuming processes that significantly limit the scalability and accuracy of biodiversity monitoring systems.While self-super...The collection and annotation of lar ge-scale bird datasets are resource-intensive and time-consuming processes that significantly limit the scalability and accuracy of biodiversity monitoring systems.While self-supervised learning(SSL)has emerged as a promising approach for leveraging unannotated data,current SSL methods face two critical challenges in bird species recognition:(1)long-tailed data distributions that result in poor performance on underrepresented species;and(2)domain shift issues caused by data augmentation strategies designed to mitigate class imbalance.Here we present SDNet,a novel SSL-based bird recognition framework that integrates diffusion models with large language models(LLMs)to overcome these limitations.SDNet employs LLMs to generate semantically rich textual descriptions for tail-class species by prompting the models with species taxonomy,morphological attributes,and habitat information,producing detailed natural language priors that capture fine-grained visual characteristics(e.g.,plumage patterns,body proportions,and distinctive markings).These textual descriptions are subsequently used by a conditional diffusion model to synthesize new bird image samples through cross-attention mechanisms that fuse textual embeddings with intermediate visual feature representations during the denoising process,ensuring generated images preserve species-specific morphological details while maintaining photorealistic quality.Additionally,we incorporate a Swin Transformer as the feature extraction backbone whose hierarchical window-based attention mechanism and shifted windowing scheme enable multi-scale local feature extraction that proves particularly effective at capturing finegrained discriminative patterns(such as beak shape and feather texture)while mitigating domain shift between synthetic and original images through consistent feature representations across both data sources.SDNet is validated on both a self-constructed dataset(Bird_BXS)an d a publicly available benchmark(Birds_25),demonstrating substantial improvements over conventional SSL approaches.Our results indicate that the synergistic integration of LLMs,diffusion models,and the Swin Transformer architecture contributes significantly to recognition accuracy,particularly for rare and morphologically similar species.These findings highlight the potential of SDNet for addressing fundamental limitations of existing SSL methods in avian recognition tasks and establishing a new paradigm for efficient self-supervised learning in large-scale ornithological vision applications.展开更多
As a key carrier for the implementation of the core quality of"aesthetic creativity",the effective realization of the aesthetic value of language textbook illustrations is facing the real problems of practic...As a key carrier for the implementation of the core quality of"aesthetic creativity",the effective realization of the aesthetic value of language textbook illustrations is facing the real problems of practical disconnection and theoretical gap.Based on the theories of semiotics,embodied cognition and cultural reproduction,this paper innovatively puts forward the concept of"transformation mechanism of aesthetic education",constructs a three-phase The study analyzes the dynamic transformation process of illustrations from image symbols to students'aesthetic experience.The study explains the essential characteristics of illustration as a dual symbolic system of"likenessregulation",reveals the cognitive ladder of"perception-cognition-creation"and the path of realization of embodied cognition,and points out that the current aesthetic education of illustration has the problem of instrumentalization,and that the current aesthetic education of illustration has the problem of instrumentalization.The study points out that the current aesthetic education of illustrations is plagued by instrumental alienation,cultural hegemony and aesthetic flattening,and proposes a"three-in-one"education path from the dimensions of teachers,teaching materials and culture,including improving teachers'aesthetic education,reconstructing the principles of teaching materials and dynamic revision mechanism,and constructing classroom aesthetic education communities.The study provides new perspectives and practical guidance for exploring the aesthetic value of language textbook illustrations and bridging the gap between the theories of aesthetics and pedagogy,aiming to promote the return of aesthetic education to the nature of"reconstruction of experience",and to cultivate students'aesthetic literacy and sound personality.展开更多
Educational cooperation,as the cornerstone and vanguard of people-to-people exchanges and practical cooperation between China and Africa,holds irreplaceable strategic significance for enhancing the quality of Africa&#...Educational cooperation,as the cornerstone and vanguard of people-to-people exchanges and practical cooperation between China and Africa,holds irreplaceable strategic significance for enhancing the quality of Africa's human capital and accelerating its structural transformation and modernization process.This paper employs“demand–supply–adaptation”as its core analytical framework and aims to systematically explore how the educational cooperation between China and Africa can serve Africa's goal of modernization more precisely and effectively.First,through reviewing and analyzing the domestic and international research literature,this paper clarifies the focus,paradigms,and shortcomings of existing research,identifying the knowledge contribution of this study.Second,utilizing detailed macro-level data,case studies,and comparative research methods,it comprehensively presents the multidimensional status,structural characteristics,and development trends of China–Africa educational cooperation in areas such as student exchanges,cooperative education,vocational and technical training,language and cultural exchange,and emerging digital education.This paper also deeply analyzes the pressing and specific demands placed on the education system by Africa's modernization development across key dimensions like economic diversification,industrialization,agricultural modernization,social governance upgrading,and digital transformation.Third,based on the cooperative principle of“Africa's needs and China's strengths,”this paper innovatively proposes systematic countermeasures and suggestions for constructing new,multi-level,high-quality,sustainable,and future-oriented pathways for China–Africa educational cooperation:(a)promoting the strategic focus of cooperation to extend from“hard infrastructure”support to empowering“soft infrastructure”;(b)deepening the integration of industry and education and school–enterprise collaboration to precisely align with Africa's industrial development needs;vigorously developing digital education and jointly building a smart education ecosystem to help Africa bridge the digital divide;(c)improving an evidence-based,third-party evaluation system for cooperative effectiveness and a full-process quality assurance system;and(d)promoting the collaborative participation of multiple actors including governments,schools,enterprises,think tanks,and social organizations to build a new cooperative pattern of coconstruction,co-governance,and shared benefits.展开更多
With the increasing demand for understanding skin physiology and advancing regenerative medicine,in vitro three-dimensional(3D)functional skin tissue models have become vital tools in dermatological research.These mod...With the increasing demand for understanding skin physiology and advancing regenerative medicine,in vitro three-dimensional(3D)functional skin tissue models have become vital tools in dermatological research.These models effectively mimic the complex structure and functions of human skin.This review comprehensively discusses the latest advancements in construction techniques,material selection,and applications of 3D skin models.It highlights the advantages and challenges associated with cutting-edge technologies such as layer-by-layer cell coating,3D bioprinting,bio-spray technology,and photolithographic microfabrication in creating highly realistic skin models.Moreover,it examines the wide-ranging applications of 3D skin models,includingelucidation of skin disease mechanisms,investigation of skin barrier functions,studies on skin aging and repair,hair regeneration,efficacy screening of therapeutic agents,cosmetic safety assessment,and personalized medicine.Finally,this review anticipates future trends in developing 3D skin models with greater structural and functional complexity,enhanced multifunctionality,and improved clinical translation.展开更多
It is known that correlation does not imply causality.Some relationships identified in the analysis of data are coincidental or unknown,and some are produced by real-world causality of the situation,which is problemat...It is known that correlation does not imply causality.Some relationships identified in the analysis of data are coincidental or unknown,and some are produced by real-world causality of the situation,which is problematic,since there is a need to differentiate between these two scenarios.Until recently,the proper−semantic−causality of the relationship could have been determined only by human experts from the area of expertise of the studied data.This has changed with the advance of large language models,which are often utilized as surrogates for such human experts,making the process automated and readily available to all data analysts.This motivates the main objective of this work,which is to introduce the design and implementation of a large language model-based semantic causality evaluator based on correlation analysis,together with its visual analysis model called Causal heatmap.After the implementation itself,the model is evaluated from the point of view of the quality of the visual model,from the point of view of the quality of causal evaluation based on large language models,and from the point of view of comparative analysis,while the results reached in the study highlight the usability of large language models in the task and the potential of the proposed approach in the analysis of unknown datasets.The results of the experimental evaluation demonstrate the usefulness of the Causal heatmap method,supported by the evident highlighting of interesting relationships,while suppressing irrelevant ones.展开更多
The authors consider the issue of hypothesis testing in varying-coefficient regression models with high-dimensional data.Utilizing kernel smoothing techniques,the authors propose a locally concerned U-statistic method...The authors consider the issue of hypothesis testing in varying-coefficient regression models with high-dimensional data.Utilizing kernel smoothing techniques,the authors propose a locally concerned U-statistic method to assess the overall significance of the coefficients.The authors establish that the proposed test is asymptotically normal under both the null hypothesis and local alternatives.Based on the locally concerned U-statistic,the authors further develop a globally concerned U-statistic to test whether the coefficient function is zero.A stochastic perturbation method is employed to approximate the distribution of the globally concerned test statistic.Monte Carlo simulations demonstrate the validity of the proposed test in finite samples.展开更多
Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a fr...Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.展开更多
This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to use...This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.展开更多
Background:Assess ChatGPT and Bard's effectiveness in the initial identification of articles for Otolaryngology—Head and Neck Surgery systematic literature reviews.Methods:Three PRISMA-based systematic reviews(Ja...Background:Assess ChatGPT and Bard's effectiveness in the initial identification of articles for Otolaryngology—Head and Neck Surgery systematic literature reviews.Methods:Three PRISMA-based systematic reviews(Jabbour et al.2017,Wong et al.2018,and Wu et al.2021)were replicated using ChatGPTv3.5 and Bard.Outputs(author,title,publication year,and journal)were compared to the original references and cross-referenced with medical databases for authenticity and recall.Results:Several themes emerged when comparing Bard and ChatGPT across the three reviews.Bard generated more outputs and had greater recall in Wong et al.'s review,with a broader date range in Jabbour et al.'s review.In Wu et al.'s review,ChatGPT-2 had higher recall and identified more authentic outputs than Bard-2.Conclusion:Large language models(LLMs)failed to fully replicate peer-reviewed methodologies,producing outputs with inaccuracies but identifying relevant,especially recent,articles missed by the references.While human-led PRISMA-based reviews remain the gold standard,refining LLMs for literature reviews shows potential.展开更多
Objectives:The five-year survival rate for pancreatic cancer is notably low,posing a significant challenge to patient health.The primary treatments are radiotherapy and chemotherapy,sometimes combined with targeted th...Objectives:The five-year survival rate for pancreatic cancer is notably low,posing a significant challenge to patient health.The primary treatments are radiotherapy and chemotherapy,sometimes combined with targeted therapy;however,their clinical benefits are limited.Therefore,developing new models to evaluate the therapeutic potential of novel molecules is essential.Fingolimod and Dimethyl Fumarate(DMF),currently used to treat multiple sclerosis,have recently been shown to have anti-cancer effects in several preclinical tumor models.This study aims to evaluate the therapeutic potential of Fingolimod and DMF in pancreatic cancer by investigating their respective in vitro cytotoxicity and in vivo antitumor effects.Methods:In this study,we evaluated for the first time these two drugs in pancreatic preclinical models in vitro using 3D spheroid tumor models and in vivo,which are compared to two standard-of-care consisting of Gemcitabine and Erlotinib.Results:In vitro,both Fingolimod and DMF induced cytotoxicity in spheroids from two pancreatic cell lines.Additionally,Fingolimod and DMF displayed anticancer effects in two subcutaneous xenograft models using PANC-1 and CFPAC-1 cells.Conclusions:Although the responses observed with Fingolimod and DMF were similar to those of Gemcitabine and Erlotinib,these findings indicate a potential emerging interest in Fingolimod and DMF for the treatment of pancreatic cancer.However,further work is still necessary to fully characterize how these drugs affect tumor progression.展开更多
Global Navigation Satellite System(GNSS)observations are critical for establishing high-precision terrestrial reference frames(TRF),but the environmental loading effects,particularly hydrological loading deformation(H...Global Navigation Satellite System(GNSS)observations are critical for establishing high-precision terrestrial reference frames(TRF),but the environmental loading effects,particularly hydrological loading deformation(HYLD),remain unaccounted in existing TRF like ITRF2020,limiting their accuracy.This study evaluates the performance of multiple HYLD datasets derived from GRACE(mascon and spherical harmonic(SH)products)and four hydrological models(LSDM,ERA5,GLDAS2,and MERRA2)in explaining seasonal and non-seasonal GNSS displacements globally using IGS Repro3 and Re pro 2datasets.Among these six HYLD datasets,we demonstrate that the GRACE mascon solution achieves superior performance in explaining the seasonal and non-seasonal GNSS displacements,by quantifying the amplitude reduction ratio(AMPR)and root mean square reduction ratio(RMSR)induced by HYLD corrections,respectively.The mascon-derived HYLD achieves better correction,particularly with the vertical median AMPR of 35.1%and RMSR of 4%.In contrast,hydrological models and SH product have relatively lower performance in explaining GNSS displacements,with ERA5 achieving only 24.7%for the ve rtical AMPR.The HYLDs of coastal stations generally exhibit worse perfo rmance with lower AMPR and more negative RMSR distributions,likely reflecting the influence of ocean loading and their limitations in accurately isolating the land water signal within land boundaries;whereas the mascon result shows minimal differences between inland and coastal stations,benefitting from the reduced leakage of land water into the oceans.Furthermore,the transition from Repro2 to the improved reprocessing strategy in Re pro3 enhances the overall consistency between HYLDs and GNSS displacements,specifically with a 7%improvement in the vertical AMPR with MERRA2.展开更多
The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention a...The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention and treatment methods.Animal models serve as essential tools for investigating disease mechanisms and assessing novel therapeutic strategies,and the scientific rigor of their construction and validation significantly impacts the reliability of research findings.This paper systematically reviews the research progress and evaluation systems of BAS animal models over the past decade,aiming to provide a robust foundation for the optimized construction of BAS models,intervention studies,and clinical translation.This effort is intended to facilitate the innovation and advancement in BAS prevention and treatment strategies.展开更多
War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient an...War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.展开更多
基金funded by the Deanship of Postgraduate Studies and Scientific Research at Majmaah University,grant number[R-2025-1637].
文摘The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack systematic frameworks capable of addressing the contextual and pedagogical nuances required for effective implementation.This paper introduces a novel framework that combines Data-Driven Error-Correcting Output Codes(DECOC),Long Short-Term Memory(LSTM)networks,and Multi-Layer Deep Neural Networks(ML-DNN)to identify optimal emoji placements within computer science course materials.The originality of the proposed system lies in its ability to leverage sentiment analysis techniques and contextual embeddings to align emoji recommendations with both the emotional tone and learning objectives of course content.A meticulously annotated dataset,comprising diverse topics in computer science,was developed to train and validate the model,ensuring its applicability across a wide range of educational contexts.Comprehensive validation demonstrated the system’s superior performance,achieving an accuracy of 92.4%,precision of 90.7%,recall of 89.3%,and an F1-score of 90.0%.Comparative analysis with baselinemodels and relatedworks confirms themodel’s ability tooutperformexisting approaches inbalancing accuracy,relevance,and contextual appropriateness.Beyond its technical advancements,this framework offers practical benefits for educators by providing an Artificial Intelligence-assisted(AI-assisted)tool that facilitates personalized content adaptation based on student sentiment and engagement patterns.By automating the identification of appropriate emoji placements,teachers can enhance digital course materials with minimal effort,improving the clarity of complex concepts and fostering an emotionally supportive learning environment.This paper contributes to the emerging field of AI-enhanced education by addressing critical gaps in personalized content delivery and pedagogical support.Its findings highlight the transformative potential of integrating AI-driven emoji placement systems into educational materials,offering an innovative tool for fostering student engagement and enhancing learning outcomes.The proposed framework establishes a foundation for future advancements in the visual augmentation of educational resources,emphasizing scalability and adaptability for broader applications in e-learning.
基金Sponsored by the Ability Enhancement Project of Teaching Staff in Harbin Institute of Technology(Grant No.06)
文摘In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new and successful educational data mining models were analyzed and compared. These models have better performance than traditional models( such as Knowledge Tracing Model) in efficiency,comprehensiveness,ease of use,stability and so on. Then,the neural network algorithm was conducted to explore the feasibility of the application of educational data mining in student management,and the results show that it has enough predictive accuracy and reliability to be put into practice. In the end,the possibility and prospect of the application of educational data mining in teaching management system for university students was assessed.
基金Henan Province Higher Education Teaching Reform Research and Practice Project“Industry Guidance,Integration of Medical Education,and Professional Reality:Innovation and Practice of Medical Technology(1+2)Education Model”(2024SJGLX0725)Henan Province Medical Education Research Project“Research on the Innovation and Practice of Talent Training Model for Rehabilitation Therapy Technology Majors Based on Collaborative Education between Medicine and Education”(WJLX2023208)Zhengzhou Local College Teaching Reform Research and Practice Project“Research and Practice on the Talent Training Model of Rehabilitation Therapy Technology Based on the Integration of Industry and Education”(ZZJG-A1033)。
文摘This study empirically analyzes the application effect of the integration of medical and educational models in cultivating professional abilities in traditional Chinese medicine rehabilitation techniques.The research subjects are 100 students from the Traditional Chinese Medicine Rehabilitation Technology major at Y school.Through questionnaire scores,practical training results,and interview data,this study explores the outcomes of this integrated approach.The findings reveal that students in the experimental group significantly outperform those in the control group in terms of practical operation skills,professional responsibility,and communication and collaboration skills.This research confirms the notable role of the medical-educational integration model in enhancing the professional skills and accomplishments of students majoring in traditional Chinese medicine rehabilitation,providing a scientific basis for vocational education reform and the cultivation of rehabilitation technical talents.
文摘This paper introduces a new version of the open-source educational software, LESM (Linear Elements Structure Model), developed in MATLAB for structural analysis of one-dimensional models such as frames, trusses, and grillages. The updated program includes dynamic analysis, which incorporates inertial and damping effects, time-dependent load conditions, and a transient solver with multiple time integration schemes. The software assumes small displacements and linear-elastic material behavior. The paper briefly explains the theoretical basis for these developments and the reorganization of the source code using Object-Oriented Programming (OOP). The updated Graphical User Interface (GUI) allows interactive use of dynamic analysis features and displays new results such as animations, envelope diagrams of internal forces, phase portraits, and the response of degrees-of-freedom in time and frequency domain. The new version was used in a structural dynamics course, and new assignments were elaborated to improve students’ understanding of the subject.
基金funded by the National Key Research and Development Program of China(No.2021YFA1100500)the National Natural Science Foundation of China(No.82370662)the Key Research&Development Plan of Zhejiang Province(No.2024C03051).
文摘This study evaluated the accuracy,completeness,and comprehensibility of responses from mainstream large language models(LLMs)to hepatitis C virus(HCV)-related questions,aiming to assess their performance in addressing patient queries about disease and lifestyle behaviors.The models selected were ChatGPT-4o,Gemini 2.0 Pro,Claude 3.5 Sonnet,and DeepSeek V3,with 12 questions chosen by two HCV experts from the domains of prevention,diagnosis,and treatment.
基金supported by the National Key R&D Program of China[2022YFF0902703]the State Administration for Market Regulation Science and Technology Plan Project(2024MK033).
文摘Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.
基金supported by the National Natural Science Foundation of China(32471964)。
文摘The collection and annotation of lar ge-scale bird datasets are resource-intensive and time-consuming processes that significantly limit the scalability and accuracy of biodiversity monitoring systems.While self-supervised learning(SSL)has emerged as a promising approach for leveraging unannotated data,current SSL methods face two critical challenges in bird species recognition:(1)long-tailed data distributions that result in poor performance on underrepresented species;and(2)domain shift issues caused by data augmentation strategies designed to mitigate class imbalance.Here we present SDNet,a novel SSL-based bird recognition framework that integrates diffusion models with large language models(LLMs)to overcome these limitations.SDNet employs LLMs to generate semantically rich textual descriptions for tail-class species by prompting the models with species taxonomy,morphological attributes,and habitat information,producing detailed natural language priors that capture fine-grained visual characteristics(e.g.,plumage patterns,body proportions,and distinctive markings).These textual descriptions are subsequently used by a conditional diffusion model to synthesize new bird image samples through cross-attention mechanisms that fuse textual embeddings with intermediate visual feature representations during the denoising process,ensuring generated images preserve species-specific morphological details while maintaining photorealistic quality.Additionally,we incorporate a Swin Transformer as the feature extraction backbone whose hierarchical window-based attention mechanism and shifted windowing scheme enable multi-scale local feature extraction that proves particularly effective at capturing finegrained discriminative patterns(such as beak shape and feather texture)while mitigating domain shift between synthetic and original images through consistent feature representations across both data sources.SDNet is validated on both a self-constructed dataset(Bird_BXS)an d a publicly available benchmark(Birds_25),demonstrating substantial improvements over conventional SSL approaches.Our results indicate that the synergistic integration of LLMs,diffusion models,and the Swin Transformer architecture contributes significantly to recognition accuracy,particularly for rare and morphologically similar species.These findings highlight the potential of SDNet for addressing fundamental limitations of existing SSL methods in avian recognition tasks and establishing a new paradigm for efficient self-supervised learning in large-scale ornithological vision applications.
基金The 2026 Annual Project for the Improvement of Educational and Research Capabilities of Primary and Secondary School Teachers in Guangdong Province titled"Breaking Boundaries,Integration,and Empowerment:Innovative Practice Research on Teacher Training Courses for the Synergy of Aesthetic Education and Moral Education"(Host:Wenjiang Zhang)。
文摘As a key carrier for the implementation of the core quality of"aesthetic creativity",the effective realization of the aesthetic value of language textbook illustrations is facing the real problems of practical disconnection and theoretical gap.Based on the theories of semiotics,embodied cognition and cultural reproduction,this paper innovatively puts forward the concept of"transformation mechanism of aesthetic education",constructs a three-phase The study analyzes the dynamic transformation process of illustrations from image symbols to students'aesthetic experience.The study explains the essential characteristics of illustration as a dual symbolic system of"likenessregulation",reveals the cognitive ladder of"perception-cognition-creation"and the path of realization of embodied cognition,and points out that the current aesthetic education of illustration has the problem of instrumentalization,and that the current aesthetic education of illustration has the problem of instrumentalization.The study points out that the current aesthetic education of illustrations is plagued by instrumental alienation,cultural hegemony and aesthetic flattening,and proposes a"three-in-one"education path from the dimensions of teachers,teaching materials and culture,including improving teachers'aesthetic education,reconstructing the principles of teaching materials and dynamic revision mechanism,and constructing classroom aesthetic education communities.The study provides new perspectives and practical guidance for exploring the aesthetic value of language textbook illustrations and bridging the gap between the theories of aesthetics and pedagogy,aiming to promote the return of aesthetic education to the nature of"reconstruction of experience",and to cultivate students'aesthetic literacy and sound personality.
文摘Educational cooperation,as the cornerstone and vanguard of people-to-people exchanges and practical cooperation between China and Africa,holds irreplaceable strategic significance for enhancing the quality of Africa's human capital and accelerating its structural transformation and modernization process.This paper employs“demand–supply–adaptation”as its core analytical framework and aims to systematically explore how the educational cooperation between China and Africa can serve Africa's goal of modernization more precisely and effectively.First,through reviewing and analyzing the domestic and international research literature,this paper clarifies the focus,paradigms,and shortcomings of existing research,identifying the knowledge contribution of this study.Second,utilizing detailed macro-level data,case studies,and comparative research methods,it comprehensively presents the multidimensional status,structural characteristics,and development trends of China–Africa educational cooperation in areas such as student exchanges,cooperative education,vocational and technical training,language and cultural exchange,and emerging digital education.This paper also deeply analyzes the pressing and specific demands placed on the education system by Africa's modernization development across key dimensions like economic diversification,industrialization,agricultural modernization,social governance upgrading,and digital transformation.Third,based on the cooperative principle of“Africa's needs and China's strengths,”this paper innovatively proposes systematic countermeasures and suggestions for constructing new,multi-level,high-quality,sustainable,and future-oriented pathways for China–Africa educational cooperation:(a)promoting the strategic focus of cooperation to extend from“hard infrastructure”support to empowering“soft infrastructure”;(b)deepening the integration of industry and education and school–enterprise collaboration to precisely align with Africa's industrial development needs;vigorously developing digital education and jointly building a smart education ecosystem to help Africa bridge the digital divide;(c)improving an evidence-based,third-party evaluation system for cooperative effectiveness and a full-process quality assurance system;and(d)promoting the collaborative participation of multiple actors including governments,schools,enterprises,think tanks,and social organizations to build a new cooperative pattern of coconstruction,co-governance,and shared benefits.
文摘With the increasing demand for understanding skin physiology and advancing regenerative medicine,in vitro three-dimensional(3D)functional skin tissue models have become vital tools in dermatological research.These models effectively mimic the complex structure and functions of human skin.This review comprehensively discusses the latest advancements in construction techniques,material selection,and applications of 3D skin models.It highlights the advantages and challenges associated with cutting-edge technologies such as layer-by-layer cell coating,3D bioprinting,bio-spray technology,and photolithographic microfabrication in creating highly realistic skin models.Moreover,it examines the wide-ranging applications of 3D skin models,includingelucidation of skin disease mechanisms,investigation of skin barrier functions,studies on skin aging and repair,hair regeneration,efficacy screening of therapeutic agents,cosmetic safety assessment,and personalized medicine.Finally,this review anticipates future trends in developing 3D skin models with greater structural and functional complexity,enhanced multifunctionality,and improved clinical translation.
基金supported by University Grant Agency of Matej Bel University in Banská Bystrica project number UGA-14-PDS-2025.
文摘It is known that correlation does not imply causality.Some relationships identified in the analysis of data are coincidental or unknown,and some are produced by real-world causality of the situation,which is problematic,since there is a need to differentiate between these two scenarios.Until recently,the proper−semantic−causality of the relationship could have been determined only by human experts from the area of expertise of the studied data.This has changed with the advance of large language models,which are often utilized as surrogates for such human experts,making the process automated and readily available to all data analysts.This motivates the main objective of this work,which is to introduce the design and implementation of a large language model-based semantic causality evaluator based on correlation analysis,together with its visual analysis model called Causal heatmap.After the implementation itself,the model is evaluated from the point of view of the quality of the visual model,from the point of view of the quality of causal evaluation based on large language models,and from the point of view of comparative analysis,while the results reached in the study highlight the usability of large language models in the task and the potential of the proposed approach in the analysis of unknown datasets.The results of the experimental evaluation demonstrate the usefulness of the Causal heatmap method,supported by the evident highlighting of interesting relationships,while suppressing irrelevant ones.
基金supported by the National Social Science Foundation of China under Grant No.23&ZD126National Science Foundation of China under Grant No.12471256+1 种基金Natural Science Foundation of Shanxi Province under Grant No.202203021221219Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi under Grant No.2023L164。
文摘The authors consider the issue of hypothesis testing in varying-coefficient regression models with high-dimensional data.Utilizing kernel smoothing techniques,the authors propose a locally concerned U-statistic method to assess the overall significance of the coefficients.The authors establish that the proposed test is asymptotically normal under both the null hypothesis and local alternatives.Based on the locally concerned U-statistic,the authors further develop a globally concerned U-statistic to test whether the coefficient function is zero.A stochastic perturbation method is employed to approximate the distribution of the globally concerned test statistic.Monte Carlo simulations demonstrate the validity of the proposed test in finite samples.
文摘Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.
基金funded by the Office of the Vice-President for Research and Development of Cebu Technological University.
文摘This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.
文摘Background:Assess ChatGPT and Bard's effectiveness in the initial identification of articles for Otolaryngology—Head and Neck Surgery systematic literature reviews.Methods:Three PRISMA-based systematic reviews(Jabbour et al.2017,Wong et al.2018,and Wu et al.2021)were replicated using ChatGPTv3.5 and Bard.Outputs(author,title,publication year,and journal)were compared to the original references and cross-referenced with medical databases for authenticity and recall.Results:Several themes emerged when comparing Bard and ChatGPT across the three reviews.Bard generated more outputs and had greater recall in Wong et al.'s review,with a broader date range in Jabbour et al.'s review.In Wu et al.'s review,ChatGPT-2 had higher recall and identified more authentic outputs than Bard-2.Conclusion:Large language models(LLMs)failed to fully replicate peer-reviewed methodologies,producing outputs with inaccuracies but identifying relevant,especially recent,articles missed by the references.While human-led PRISMA-based reviews remain the gold standard,refining LLMs for literature reviews shows potential.
基金supported by Porsolt SAS,https://www.porsolt.com/.
文摘Objectives:The five-year survival rate for pancreatic cancer is notably low,posing a significant challenge to patient health.The primary treatments are radiotherapy and chemotherapy,sometimes combined with targeted therapy;however,their clinical benefits are limited.Therefore,developing new models to evaluate the therapeutic potential of novel molecules is essential.Fingolimod and Dimethyl Fumarate(DMF),currently used to treat multiple sclerosis,have recently been shown to have anti-cancer effects in several preclinical tumor models.This study aims to evaluate the therapeutic potential of Fingolimod and DMF in pancreatic cancer by investigating their respective in vitro cytotoxicity and in vivo antitumor effects.Methods:In this study,we evaluated for the first time these two drugs in pancreatic preclinical models in vitro using 3D spheroid tumor models and in vivo,which are compared to two standard-of-care consisting of Gemcitabine and Erlotinib.Results:In vitro,both Fingolimod and DMF induced cytotoxicity in spheroids from two pancreatic cell lines.Additionally,Fingolimod and DMF displayed anticancer effects in two subcutaneous xenograft models using PANC-1 and CFPAC-1 cells.Conclusions:Although the responses observed with Fingolimod and DMF were similar to those of Gemcitabine and Erlotinib,these findings indicate a potential emerging interest in Fingolimod and DMF for the treatment of pancreatic cancer.However,further work is still necessary to fully characterize how these drugs affect tumor progression.
基金sponsored by the National Natural Science Foundation of China,China(Grant Nos.42174028,42474030,and 41774007)Major Science and Technology Program of Hubei Province,China(Grant No.JSCX202501188)the Natural Science Foundation of Wuhan,China(Grant No.2024040701010029)。
文摘Global Navigation Satellite System(GNSS)observations are critical for establishing high-precision terrestrial reference frames(TRF),but the environmental loading effects,particularly hydrological loading deformation(HYLD),remain unaccounted in existing TRF like ITRF2020,limiting their accuracy.This study evaluates the performance of multiple HYLD datasets derived from GRACE(mascon and spherical harmonic(SH)products)and four hydrological models(LSDM,ERA5,GLDAS2,and MERRA2)in explaining seasonal and non-seasonal GNSS displacements globally using IGS Repro3 and Re pro 2datasets.Among these six HYLD datasets,we demonstrate that the GRACE mascon solution achieves superior performance in explaining the seasonal and non-seasonal GNSS displacements,by quantifying the amplitude reduction ratio(AMPR)and root mean square reduction ratio(RMSR)induced by HYLD corrections,respectively.The mascon-derived HYLD achieves better correction,particularly with the vertical median AMPR of 35.1%and RMSR of 4%.In contrast,hydrological models and SH product have relatively lower performance in explaining GNSS displacements,with ERA5 achieving only 24.7%for the ve rtical AMPR.The HYLDs of coastal stations generally exhibit worse perfo rmance with lower AMPR and more negative RMSR distributions,likely reflecting the influence of ocean loading and their limitations in accurately isolating the land water signal within land boundaries;whereas the mascon result shows minimal differences between inland and coastal stations,benefitting from the reduced leakage of land water into the oceans.Furthermore,the transition from Repro2 to the improved reprocessing strategy in Re pro3 enhances the overall consistency between HYLDs and GNSS displacements,specifically with a 7%improvement in the vertical AMPR with MERRA2.
基金National Natural Science Foundation of China,Grant/Award Number:82000102 and 82270112。
文摘The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention and treatment methods.Animal models serve as essential tools for investigating disease mechanisms and assessing novel therapeutic strategies,and the scientific rigor of their construction and validation significantly impacts the reliability of research findings.This paper systematically reviews the research progress and evaluation systems of BAS animal models over the past decade,aiming to provide a robust foundation for the optimized construction of BAS models,intervention studies,and clinical translation.This effort is intended to facilitate the innovation and advancement in BAS prevention and treatment strategies.
文摘War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.
