Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal ...Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowled...Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowledge graph reasoning is more challenging due to its temporal nature.In essence,within each time step in a dynamic knowledge graph,there exists structural dependencies among entities and relations,whereas between adjacent time steps,there exists temporal continuity.Based on these structural and temporal characteristics,we propose a model named“DKGR-DR”to learn distributed representations of entities and relations by combining recurrent neural networks and graph neural networks to capture structural dependencies and temporal continuity in DKGs.In addition,we construct a static attribute graph to represent entities’inherent properties.DKGR-DR is capable of modeling both dynamic and static aspects of entities,enabling effective entity prediction and relation prediction.We conduct experiments on ICEWS05-15,ICEWS18,and ICEWS14 to demonstrate that DKGR-DR achieves competitive performance.展开更多
Artificial intelligence has experienced a significant boom with the emergence of agentic AI,where autonomous agents are increasingly replacing human intervention,enabling systems to perceive,reason,and act independent...Artificial intelligence has experienced a significant boom with the emergence of agentic AI,where autonomous agents are increasingly replacing human intervention,enabling systems to perceive,reason,and act independently to achieve specific goals.Despite its transformative potential,comprehensive information on agentic AI remains scarce in the literature.This paper provides the first comprehensive review of agentic AI,focusing on its evolution and three core aspects:patterns,types,and environments.The evolution of agentic AI is traced through five phases to the current era of multi-modal and collaborative agents,driven by advancements in reinforcement learning,neural networks,and large language models(LLMs).Five key patterns:tool use,reflection,ReAct,planning,and multi-agent collaboration(MAC)define how agentic AI systems interact and process tasks.These systems are categorized into seven categories,each tailored for specific operational styles and autonomy in decision making.The environments in which these agents operate are classified as static,dynamic,fully observable,partially observable,deterministic,stochastic,single-agent,and multiagent,emphasizing the impact of environmental complexity on agent behavior.Agentic AI has revolutionized systems through autonomous decision making and resource optimization,yet challenges persist in aligning AI with human values,ensuring adaptability,and addressing ethical constraints.Future research focuses on multidomain agents,human–AI collaboration,and self-improving systems.This work provides researchers,practitioners,and policymakers with a structured approach to understanding and advancing the rapidly evolving landscape of agentic AI systems.展开更多
This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal...This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal factors and their performance changes in hazardous chemical operational accidents, along with determining the functional failure link relationships. Subsequently, FERM was employed to elucidate both qualitative and quantitative operational accident information within a unified framework, which could be regarded as the input of information fusion to obtain the fuzzy belief distribution of each cause factor. Finally, the derived risk values of the causal factors were ranked while constructing multi-level accident causation chains to unveil the weak links in system functionality and the primary roots of operational accidents. Using the specific case of the “1·15” major explosion and fire accident at Liaoning Panjin Haoye Chemical Co., Ltd., seven causal factors and their corresponding performance changes were identified. Additionally, five accident causation chains were uncovered based on the fuzzy joint distribution of the functional assessment level(FAL) and reliability distribution(RD),revealing an overall increase in risk along the accident evolution path. The research findings demonstrated that FERM enabled the effective characterization, rational quantification and accurate analysis of the inherent uncertainties in hazardous chemical operational accident risks from a systemic perspective.展开更多
Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the know...Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the knowledge graph(KG)to text-enhanced retrievalaugmented generation(KG2TRAG)method.Methods The TCM lung cancer model(TCMLCM)was constructed by fine-tuning Chat-GLM2-6B on the specialized datasets Tianchi TCM,HuangDi,and ShenNong-TCM-Dataset,as well as a TCM lung cancer KG.The KG2TRAG method was applied to enhance the knowledge retrieval,which can convert KG triples into natural language text via ChatGPT-aided linearization,leveraging large language models(LLMs)for context-aware reasoning.For a comprehensive comparison,MedicalGPT,HuatuoGPT,and BenTsao were selected as the baseline models.Performance was evaluated using bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),accuracy,and the domain-specific TCM-LCEval metrics,with validation from TCM oncology experts assessing answer accuracy,professionalism,and usability.Results The TCMLCM model achieved the optimal performance across all metrics,including a BLEU score of 32.15%,ROUGE-L of 59.08%,and an accuracy rate of 79.68%.Notably,in the TCM-LCEval assessment specific to the field of TCM,its performance was 3%−12%higher than that of the baseline model.Expert evaluations highlighted superior performance in accuracy and professionalism.Conclusion TCMLCM can provide an innovative solution for TCM lung cancer QA,demonstrating the feasibility of integrating structured KGs with LLMs.This work advances intelligent TCM healthcare tools and lays a foundation for future AI-driven applications in traditional medicine.展开更多
Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,ca...Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,called event evolution patterns,implying informative temporal dependencies between events.Recently,many extrapolation works on TKGs have been devoted to modelling these evolutional patterns,but the task is still far from resolved because most existing works simply rely on encoding these patterns into entity representations while overlooking the significant information implied by relations of evolutional patterns.However,the authors realise that the temporal dependencies inherent in the relations of these event evolution patterns may guide the follow-up event prediction to some extent.To this end,a Temporal Relational Context-based Temporal Dependencies Learning Network(TRenD)is proposed to explore the temporal context of relations for more comprehensive learning of event evolution patterns,especially those temporal dependencies caused by interactive patterns of relations.Trend incorporates a semantic context unit to capture semantic correlations between relations,and a structural context unit to learn the interaction pattern of relations.By learning the temporal contexts of relations semantically and structurally,the authors gain insights into the underlying event evolution patterns,enabling to extract comprehensive historical information for future prediction better.Experimental results on benchmark datasets demonstrate the superiority of the model.展开更多
Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power i...Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power industry,there would be more possibilities for knowledge graph to be utilized.However,as a complex cause-and-effect network,the electric power domain knowledge graph has massive nodes,heterogeneous edges,and sparse structures.Thus,it requires human effort to process data,while quality and accuracy cannot be guaranteed.We propose a novel graph computing-based knowledge reasoning method that takes into account the sparsity of the electric power domain knowledge graph to solve the aforementioned problems and achieve improved accuracy of graph classification and knowledge reasoning tasks.The Haar basis is constructed to realize fast calculation,while the multiscale network structure is introduced to assure classification accuracy and generalization.We evaluate the proposed algorithm on the NCI-1,CEPRI UHVP,and CEPRI EQUIP databases.Simulation results demonstrate its superior performance in terms of accuracy and loss.展开更多
The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the ...The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the lack of high-quality cross-modal correspondence methods.Existing approaches often attempt to establish modality correspondence by extracting shared features across different modalities.However,these methods tend to focus on local information extraction and fail to fully leverage the global identity information in the cross-modal features,resulting in limited correspondence accuracy and suboptimal matching performance.To address this issue,we propose a quadratic graph matching method designed to overcome the challenges posed by modality differences through precise cross-modal relationship alignment.This method transforms the cross-modal correspondence problem into a graph matching task and minimizes the matching cost using a center search mechanism.Building on this approach,we further design a block reasoning module to uncover latent relationships between person identities and optimize the modality correspondence results.The block strategy not only improves the efficiency of updating gallery images but also enhances matching accuracy while reducing computational load.Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on the SYSU-MM01,RegDB,and RGBNT201 datasets,achieving excellent matching accuracy and robustness,thereby validating its effectiveness in cross-modal person re-identification.展开更多
BACKGROUND Patients with major depression(MD)exhibit conditional reasoning dysfunction;however,no studies on the event-related potential(ERP)characteristics of conditional reasoning in MD have been reported.AIM To inv...BACKGROUND Patients with major depression(MD)exhibit conditional reasoning dysfunction;however,no studies on the event-related potential(ERP)characteristics of conditional reasoning in MD have been reported.AIM To investigate the ERP characteristics of conditional reasoning in MD patients and explore the neural mechanism of cognitive processing.METHODS Thirty-four patients with MD and 34 healthy controls(HCs)completed ERP measurements while performing the Wason selection task(WST).The clusterbased permutation test in FieldTrip was used to compare the differences in the mean amplitudes between the patients with MD and HCs on the ERP components under different experimental conditions.Behavioral data[accuracy(ACC)and reaction times(RTs)],the ERP P100 and late positive potentials(LPPs)were analyzed.RESULTS Although the mean ACC was greater and the mean of RTs was shorter in HCs than in MD patients,the differences were not statistically significant.However,across both groups,the ACC in the precautionary WST was greater than that in the other tasks,and the RTs in the abstract task were greater than those in the other tasks.Importantly,compared with that of HCs,the P100 of the left centroparietal sites was significantly increased,and the early LPP was attenuated at parietal sites and increased at left frontocentral sites;the medium LPP and late LPP were increased at the left frontocentral sites.CONCLUSION Patients with MD have conditional reasoning dysfunction and exhibit abnormal ERP characteristics evoked by the WST,which suggests neural correlates of abnormalities in conditional reasoning function in MD patients.展开更多
The evidential reasoning(ER)rule framework has been widely applied in multi-attribute decision analysis and system assessment to manage uncertainty.However,traditional ER implementations rely on two critical limitatio...The evidential reasoning(ER)rule framework has been widely applied in multi-attribute decision analysis and system assessment to manage uncertainty.However,traditional ER implementations rely on two critical limitations:1)unrealistic assumptions of complete evidence independence,and 2)a lack of mechanisms to differentiate causal relationships from spurious correlations.Existing similarity-based approaches often misinterpret interdependent evidence,leading to unreliable decision outcomes.To address these gaps,this study proposes a causality-enhanced ER rule(CER-e)framework with three key methodological innovations:1)a multidimensional causal representation of evidence to capture dependency structures;2)probabilistic quantification of causal strength using transfer entropy,a model-free information-theoretic measure;3)systematic integration of causal parameters into the ER inference process while maintaining evidential objectivity.The PC algorithm is employed during causal discovery to eliminate spurious correlations,ensuring robust causal inference.Case studies in two types of domains—telecommunications network security assessment and structural risk evaluation—validate CER-e’s effectiveness in real-world scenarios.Under simulated incomplete information conditions,the framework demonstrates superior algorithmic robustness compared to traditional ER.Comparative analyses show that CER-e significantly improves both the interpretability of causal relationships and the reliability of assessment results,establishing a novel paradigm for integrating causal inference with evidential reasoning in complex system evaluation.展开更多
In this paper,a robust and consistent COVID-19 emergency decision-making approach is proposed based on q-rung linear diophantine fuzzy set(q-RLDFS),differential evolutionary(DE)optimization principles,and evidential r...In this paper,a robust and consistent COVID-19 emergency decision-making approach is proposed based on q-rung linear diophantine fuzzy set(q-RLDFS),differential evolutionary(DE)optimization principles,and evidential reasoning(ER)methodology.The proposed approach uses q-RLDFS in order to represent the evaluating values of the alternatives corresponding to the attributes.DE optimization is used to obtain the optimal weights of the attributes,and ER methodology is used to compute the aggregated q-rung linear diophantine fuzzy values(q-RLDFVs)of each alternative.Then the score values of alternatives are computed based on the aggregated q-RLDFVs.An alternative with the maximum score value is selected as a better one.The applicability of the proposed approach has been illustrated in COVID-19 emergency decision-making system and sustainable energy planning management.Moreover,we have validated the proposed approach with a numerical example.Finally,a comparative study is provided with the existing models,where the proposed approach is found to be robust to perform better and consistent in uncertain environments.展开更多
This study investigated the relationship between parental cognitive ability and child logical reasoning ability,and the role of academic expectation and family environment in that relationship.Based on the 2020 China ...This study investigated the relationship between parental cognitive ability and child logical reasoning ability,and the role of academic expectation and family environment in that relationship.Based on the 2020 China Family Panel Studies(CFPS)data,1491 children(girls ratio=53.78%;average grade=6.023 years,school grade standard deviation=1.825 years).Results following multiple regression model(OLS)show that the higher the parental cognitive ability,the higher the children’s logical reasoning ability.Secondly,parental academic expectation serves as a mediator between their cognitive ability and children’s logical reasoning ability for higher logical reasoning by children.Third,a possible family environment acts as a mediator in the relationship between parents’cognitive ability and children’s logical reasoning ability to be higher.We conclude from thesefindings that parents with high cognitive abilities can enhance their children’s logical reasoning skills not only by setting higher academic expectations,but also by cultivating a supportive family environment.Thesefindings imply a need for intervention to improve family quality of life to enhance children’s thinking abilities to optimize their academic learning.展开更多
Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step...Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.展开更多
Aiming at the characteristics of autonomy,confrontation,and uncertainty in unmanned aerial vehicle(UAV)swarm operations,case-based reasoning(CBR)technology with advantages such as weak dependence on domain knowledge a...Aiming at the characteristics of autonomy,confrontation,and uncertainty in unmanned aerial vehicle(UAV)swarm operations,case-based reasoning(CBR)technology with advantages such as weak dependence on domain knowledge and efficient problem-solving is introduced,and a recommendation method for UAV swarm operation strategies based on CBR is proposed.Firstly,we design a universal framework for UAV swarm operation strategies from three dimensions:operation effectiveness,time,and cost.Secondly,based on the representation of operation cases,certain,fuzzy,interval,and classification attribute similarity calculation methods,as well as entropybased attribute weight allocation methods,are suggested to support the calculation of global similarity of cases.This method is utilized to match the source case with the most similarity from the historical case library,to obtain the optimal recommendation strategy for the target case.Finally,in the form of red blue confrontation,a UAV swarm operation strategy recommendation case is constructed based on actual battle cases,and a system simulation analysis is conducted.The results show that the strategy given in the example performs the best in three evaluation indicators,including cost-effectiveness,and overall outperforms other operation strategies.Therefore,the proposed method has advantages such as high real-time performance and interpretability,and can address the issue of recommending UAV swarm operation strategies in complex battlefield environments across both online and offline modes.At the same time,this study could also provide new ideas for the selection of UAV swarm operation strategies.展开更多
The(3+1)-dimensional Boiti-Leon-Manna-Pempinelli(BLMP)equation serves as a crucial nonlinear evolution equation in mathematical physics,capable of characterizing complex nonlinear dynamic phenomena in three-dimensiona...The(3+1)-dimensional Boiti-Leon-Manna-Pempinelli(BLMP)equation serves as a crucial nonlinear evolution equation in mathematical physics,capable of characterizing complex nonlinear dynamic phenomena in three-dimensional space and one-dimensional time.With broad applications spanning fluid dynamics,shallow water waves,plasma physics,and condensed matter physics,the investigation of its solutions holds significant importance.Traditional analytical methods face limitations due to their dependence on bilinear forms.To overcome this constraint,this letter proposes a novel multi-modal neurosymbolic reasoning intelligent algorithm(MMNRIA)that achieves 100%accurate solutions for nonlinear partial differential equations without requiring bilinear transformations.By synergistically integrating neural networks with symbolic computation,this approach establishes a new paradigm for universal analytical solutions of nonlinear partial differential equations.As a practical demonstration,we successfully derive several exact analytical solutions for the(3+1)-dimensional BLMP equation using MMNRIA.These solutions provide a powerful theoretical framework for studying intricate wave phenomena governed by nonlinearity and dispersion effects in three-dimensional physical space.展开更多
Aiming at practical demands of manufacturing enterprises to the CAPP system in the Internet age, the CAPP model is presented based on Web and featured by open, universality and intelligence. A CAPP software package is...Aiming at practical demands of manufacturing enterprises to the CAPP system in the Internet age, the CAPP model is presented based on Web and featured by open, universality and intelligence. A CAPP software package is developed with three layer structures （the database, the Web server and the client server） to realize CAPP online services. In the CAPP software package, a new process planning method called the successive casebased reasoning is presented. Using the method, process planning procedures are divided into three layers （the process planning, the process procedure and the process step）, which are treated with the successive process reasoning. Process planning rules can be regularly described due to the granularity-based rule classification. The CAPP software package combines CAPP software with online services. The process planning has the features of variant analogy and generative creation due to adopting the successive case-based reasoning, thus improving the universality and the practicability of the process planning.展开更多
presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic co...presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic consequence relation with the connective-free form can be represented by ADRFs.展开更多
The current extended fuzzy description logics lack reasoning algorithms with TBoxes. The problem of the satisfiability of the extended fuzzy description logic EFALC cut concepts w. r. t. TBoxes is proposed, and a reas...The current extended fuzzy description logics lack reasoning algorithms with TBoxes. The problem of the satisfiability of the extended fuzzy description logic EFALC cut concepts w. r. t. TBoxes is proposed, and a reasoning algorithm is given. This algorithm is designed in the style of tableau algorithms, which is usually used in classical description logics. The transformation rules and the process of this algorithm is described and optimized with three main techniques： recursive procedure call, branch cutting and introducing sets of mesne results. The optimized algorithm is proved sound, complete and with an EXPTime complexity, and the satisfiability problem is EXPTime-complete.展开更多
文摘Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金supported byNationalNatural Science Foundation of China(GrantNos.62071098,U24B20128)Sichuan Science and Technology Program(Grant No.2022YFG0319).
文摘Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowledge graph reasoning is more challenging due to its temporal nature.In essence,within each time step in a dynamic knowledge graph,there exists structural dependencies among entities and relations,whereas between adjacent time steps,there exists temporal continuity.Based on these structural and temporal characteristics,we propose a model named“DKGR-DR”to learn distributed representations of entities and relations by combining recurrent neural networks and graph neural networks to capture structural dependencies and temporal continuity in DKGs.In addition,we construct a static attribute graph to represent entities’inherent properties.DKGR-DR is capable of modeling both dynamic and static aspects of entities,enabling effective entity prediction and relation prediction.We conduct experiments on ICEWS05-15,ICEWS18,and ICEWS14 to demonstrate that DKGR-DR achieves competitive performance.
文摘Artificial intelligence has experienced a significant boom with the emergence of agentic AI,where autonomous agents are increasingly replacing human intervention,enabling systems to perceive,reason,and act independently to achieve specific goals.Despite its transformative potential,comprehensive information on agentic AI remains scarce in the literature.This paper provides the first comprehensive review of agentic AI,focusing on its evolution and three core aspects:patterns,types,and environments.The evolution of agentic AI is traced through five phases to the current era of multi-modal and collaborative agents,driven by advancements in reinforcement learning,neural networks,and large language models(LLMs).Five key patterns:tool use,reflection,ReAct,planning,and multi-agent collaboration(MAC)define how agentic AI systems interact and process tasks.These systems are categorized into seven categories,each tailored for specific operational styles and autonomy in decision making.The environments in which these agents operate are classified as static,dynamic,fully observable,partially observable,deterministic,stochastic,single-agent,and multiagent,emphasizing the impact of environmental complexity on agent behavior.Agentic AI has revolutionized systems through autonomous decision making and resource optimization,yet challenges persist in aligning AI with human values,ensuring adaptability,and addressing ethical constraints.Future research focuses on multidomain agents,human–AI collaboration,and self-improving systems.This work provides researchers,practitioners,and policymakers with a structured approach to understanding and advancing the rapidly evolving landscape of agentic AI systems.
基金supported by the National Key Research&Development Program of China(2021YFB3301100)the National Natural Science Foundation of China(52004014)the Fundamental Research Funds for the Central Universities(ZY2406).
文摘This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal factors and their performance changes in hazardous chemical operational accidents, along with determining the functional failure link relationships. Subsequently, FERM was employed to elucidate both qualitative and quantitative operational accident information within a unified framework, which could be regarded as the input of information fusion to obtain the fuzzy belief distribution of each cause factor. Finally, the derived risk values of the causal factors were ranked while constructing multi-level accident causation chains to unveil the weak links in system functionality and the primary roots of operational accidents. Using the specific case of the “1·15” major explosion and fire accident at Liaoning Panjin Haoye Chemical Co., Ltd., seven causal factors and their corresponding performance changes were identified. Additionally, five accident causation chains were uncovered based on the fuzzy joint distribution of the functional assessment level(FAL) and reliability distribution(RD),revealing an overall increase in risk along the accident evolution path. The research findings demonstrated that FERM enabled the effective characterization, rational quantification and accurate analysis of the inherent uncertainties in hazardous chemical operational accident risks from a systemic perspective.
基金Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_2145).
文摘Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the knowledge graph(KG)to text-enhanced retrievalaugmented generation(KG2TRAG)method.Methods The TCM lung cancer model(TCMLCM)was constructed by fine-tuning Chat-GLM2-6B on the specialized datasets Tianchi TCM,HuangDi,and ShenNong-TCM-Dataset,as well as a TCM lung cancer KG.The KG2TRAG method was applied to enhance the knowledge retrieval,which can convert KG triples into natural language text via ChatGPT-aided linearization,leveraging large language models(LLMs)for context-aware reasoning.For a comprehensive comparison,MedicalGPT,HuatuoGPT,and BenTsao were selected as the baseline models.Performance was evaluated using bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),accuracy,and the domain-specific TCM-LCEval metrics,with validation from TCM oncology experts assessing answer accuracy,professionalism,and usability.Results The TCMLCM model achieved the optimal performance across all metrics,including a BLEU score of 32.15%,ROUGE-L of 59.08%,and an accuracy rate of 79.68%.Notably,in the TCM-LCEval assessment specific to the field of TCM,its performance was 3%−12%higher than that of the baseline model.Expert evaluations highlighted superior performance in accuracy and professionalism.Conclusion TCMLCM can provide an innovative solution for TCM lung cancer QA,demonstrating the feasibility of integrating structured KGs with LLMs.This work advances intelligent TCM healthcare tools and lays a foundation for future AI-driven applications in traditional medicine.
基金supported in part by the National Natural Science Foundation of China(No.62302507)and the funding of Harbin Institute of Technology(Shenzhen)(No.20210035).
文摘Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,called event evolution patterns,implying informative temporal dependencies between events.Recently,many extrapolation works on TKGs have been devoted to modelling these evolutional patterns,but the task is still far from resolved because most existing works simply rely on encoding these patterns into entity representations while overlooking the significant information implied by relations of evolutional patterns.However,the authors realise that the temporal dependencies inherent in the relations of these event evolution patterns may guide the follow-up event prediction to some extent.To this end,a Temporal Relational Context-based Temporal Dependencies Learning Network(TRenD)is proposed to explore the temporal context of relations for more comprehensive learning of event evolution patterns,especially those temporal dependencies caused by interactive patterns of relations.Trend incorporates a semantic context unit to capture semantic correlations between relations,and a structural context unit to learn the interaction pattern of relations.By learning the temporal contexts of relations semantically and structurally,the authors gain insights into the underlying event evolution patterns,enabling to extract comprehensive historical information for future prediction better.Experimental results on benchmark datasets demonstrate the superiority of the model.
基金supported by National Key R&D Program of China(2020YFB0905900).
文摘Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power industry,there would be more possibilities for knowledge graph to be utilized.However,as a complex cause-and-effect network,the electric power domain knowledge graph has massive nodes,heterogeneous edges,and sparse structures.Thus,it requires human effort to process data,while quality and accuracy cannot be guaranteed.We propose a novel graph computing-based knowledge reasoning method that takes into account the sparsity of the electric power domain knowledge graph to solve the aforementioned problems and achieve improved accuracy of graph classification and knowledge reasoning tasks.The Haar basis is constructed to realize fast calculation,while the multiscale network structure is introduced to assure classification accuracy and generalization.We evaluate the proposed algorithm on the NCI-1,CEPRI UHVP,and CEPRI EQUIP databases.Simulation results demonstrate its superior performance in terms of accuracy and loss.
文摘The cross-modal person re-identification task aims to match visible and infrared images of the same individual.The main challenges in this field arise from significant modality differences between individuals and the lack of high-quality cross-modal correspondence methods.Existing approaches often attempt to establish modality correspondence by extracting shared features across different modalities.However,these methods tend to focus on local information extraction and fail to fully leverage the global identity information in the cross-modal features,resulting in limited correspondence accuracy and suboptimal matching performance.To address this issue,we propose a quadratic graph matching method designed to overcome the challenges posed by modality differences through precise cross-modal relationship alignment.This method transforms the cross-modal correspondence problem into a graph matching task and minimizes the matching cost using a center search mechanism.Building on this approach,we further design a block reasoning module to uncover latent relationships between person identities and optimize the modality correspondence results.The block strategy not only improves the efficiency of updating gallery images but also enhances matching accuracy while reducing computational load.Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on the SYSU-MM01,RegDB,and RGBNT201 datasets,achieving excellent matching accuracy and robustness,thereby validating its effectiveness in cross-modal person re-identification.
基金Supported by Wuxi Taihu Talent Project,No.WXTTP 2021the General Scientific Research Program of Wuxi Municipal Health Commission,No.M202447.
文摘BACKGROUND Patients with major depression(MD)exhibit conditional reasoning dysfunction;however,no studies on the event-related potential(ERP)characteristics of conditional reasoning in MD have been reported.AIM To investigate the ERP characteristics of conditional reasoning in MD patients and explore the neural mechanism of cognitive processing.METHODS Thirty-four patients with MD and 34 healthy controls(HCs)completed ERP measurements while performing the Wason selection task(WST).The clusterbased permutation test in FieldTrip was used to compare the differences in the mean amplitudes between the patients with MD and HCs on the ERP components under different experimental conditions.Behavioral data[accuracy(ACC)and reaction times(RTs)],the ERP P100 and late positive potentials(LPPs)were analyzed.RESULTS Although the mean ACC was greater and the mean of RTs was shorter in HCs than in MD patients,the differences were not statistically significant.However,across both groups,the ACC in the precautionary WST was greater than that in the other tasks,and the RTs in the abstract task were greater than those in the other tasks.Importantly,compared with that of HCs,the P100 of the left centroparietal sites was significantly increased,and the early LPP was attenuated at parietal sites and increased at left frontocentral sites;the medium LPP and late LPP were increased at the left frontocentral sites.CONCLUSION Patients with MD have conditional reasoning dysfunction and exhibit abnormal ERP characteristics evoked by the WST,which suggests neural correlates of abnormalities in conditional reasoning function in MD patients.
基金supported by the Natural Science Foundation of China(Nos.U22A2099,62273113,62203461,62203365)the Innovation Project of Guangxi Graduate Education under Grant YCBZ2023130by the Guangxi Higher Education Undergraduate Teaching Reform Project Key Project,grant number 2022JGZ130.
文摘The evidential reasoning(ER)rule framework has been widely applied in multi-attribute decision analysis and system assessment to manage uncertainty.However,traditional ER implementations rely on two critical limitations:1)unrealistic assumptions of complete evidence independence,and 2)a lack of mechanisms to differentiate causal relationships from spurious correlations.Existing similarity-based approaches often misinterpret interdependent evidence,leading to unreliable decision outcomes.To address these gaps,this study proposes a causality-enhanced ER rule(CER-e)framework with three key methodological innovations:1)a multidimensional causal representation of evidence to capture dependency structures;2)probabilistic quantification of causal strength using transfer entropy,a model-free information-theoretic measure;3)systematic integration of causal parameters into the ER inference process while maintaining evidential objectivity.The PC algorithm is employed during causal discovery to eliminate spurious correlations,ensuring robust causal inference.Case studies in two types of domains—telecommunications network security assessment and structural risk evaluation—validate CER-e’s effectiveness in real-world scenarios.Under simulated incomplete information conditions,the framework demonstrates superior algorithmic robustness compared to traditional ER.Comparative analyses show that CER-e significantly improves both the interpretability of causal relationships and the reliability of assessment results,establishing a novel paradigm for integrating causal inference with evidential reasoning in complex system evaluation.
文摘In this paper,a robust and consistent COVID-19 emergency decision-making approach is proposed based on q-rung linear diophantine fuzzy set(q-RLDFS),differential evolutionary(DE)optimization principles,and evidential reasoning(ER)methodology.The proposed approach uses q-RLDFS in order to represent the evaluating values of the alternatives corresponding to the attributes.DE optimization is used to obtain the optimal weights of the attributes,and ER methodology is used to compute the aggregated q-rung linear diophantine fuzzy values(q-RLDFVs)of each alternative.Then the score values of alternatives are computed based on the aggregated q-RLDFVs.An alternative with the maximum score value is selected as a better one.The applicability of the proposed approach has been illustrated in COVID-19 emergency decision-making system and sustainable energy planning management.Moreover,we have validated the proposed approach with a numerical example.Finally,a comparative study is provided with the existing models,where the proposed approach is found to be robust to perform better and consistent in uncertain environments.
基金supported by scientific research fund of Jiangxi Provincial Social Sciences“14th Five-Year Plan”(No.23SH05).
文摘This study investigated the relationship between parental cognitive ability and child logical reasoning ability,and the role of academic expectation and family environment in that relationship.Based on the 2020 China Family Panel Studies(CFPS)data,1491 children(girls ratio=53.78%;average grade=6.023 years,school grade standard deviation=1.825 years).Results following multiple regression model(OLS)show that the higher the parental cognitive ability,the higher the children’s logical reasoning ability.Secondly,parental academic expectation serves as a mediator between their cognitive ability and children’s logical reasoning ability for higher logical reasoning by children.Third,a possible family environment acts as a mediator in the relationship between parents’cognitive ability and children’s logical reasoning ability to be higher.We conclude from thesefindings that parents with high cognitive abilities can enhance their children’s logical reasoning skills not only by setting higher academic expectations,but also by cultivating a supportive family environment.Thesefindings imply a need for intervention to improve family quality of life to enhance children’s thinking abilities to optimize their academic learning.
基金National Natural Science Foundation of China(No.62176052)。
文摘Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.
基金supported by the National Natural Science Foundation of China(72101263)the Natural Science Foundation of Hunan Province(2023JJ40677).
文摘Aiming at the characteristics of autonomy,confrontation,and uncertainty in unmanned aerial vehicle(UAV)swarm operations,case-based reasoning(CBR)technology with advantages such as weak dependence on domain knowledge and efficient problem-solving is introduced,and a recommendation method for UAV swarm operation strategies based on CBR is proposed.Firstly,we design a universal framework for UAV swarm operation strategies from three dimensions:operation effectiveness,time,and cost.Secondly,based on the representation of operation cases,certain,fuzzy,interval,and classification attribute similarity calculation methods,as well as entropybased attribute weight allocation methods,are suggested to support the calculation of global similarity of cases.This method is utilized to match the source case with the most similarity from the historical case library,to obtain the optimal recommendation strategy for the target case.Finally,in the form of red blue confrontation,a UAV swarm operation strategy recommendation case is constructed based on actual battle cases,and a system simulation analysis is conducted.The results show that the strategy given in the example performs the best in three evaluation indicators,including cost-effectiveness,and overall outperforms other operation strategies.Therefore,the proposed method has advantages such as high real-time performance and interpretability,and can address the issue of recommending UAV swarm operation strategies in complex battlefield environments across both online and offline modes.At the same time,this study could also provide new ideas for the selection of UAV swarm operation strategies.
基金supported by the National Natural Science Foundation of China(Grant No.62303289)Tianyuan Fund for Mathematics of the National Natural Science Foundation of China(Grant No.12426105)+3 种基金the Scientific and Technological Innovation Programs(STIP)of Higher Education Institutions in Shanxi(Grant No.2024L022)Fundamental Research Program of Shanxi Province(Grant Nos.202403021222001 and 202203021222003)the“Wen Ying Young Scholars”Talent Project of Shanxi University(Grant Nos.138541088,138541090,and 138541127)Funded by Open Foundation of Hubei Key Laboratory of Applied Mathematics(Hubei University)(Grant No.HBAM202401).
文摘The(3+1)-dimensional Boiti-Leon-Manna-Pempinelli(BLMP)equation serves as a crucial nonlinear evolution equation in mathematical physics,capable of characterizing complex nonlinear dynamic phenomena in three-dimensional space and one-dimensional time.With broad applications spanning fluid dynamics,shallow water waves,plasma physics,and condensed matter physics,the investigation of its solutions holds significant importance.Traditional analytical methods face limitations due to their dependence on bilinear forms.To overcome this constraint,this letter proposes a novel multi-modal neurosymbolic reasoning intelligent algorithm(MMNRIA)that achieves 100%accurate solutions for nonlinear partial differential equations without requiring bilinear transformations.By synergistically integrating neural networks with symbolic computation,this approach establishes a new paradigm for universal analytical solutions of nonlinear partial differential equations.As a practical demonstration,we successfully derive several exact analytical solutions for the(3+1)-dimensional BLMP equation using MMNRIA.These solutions provide a powerful theoretical framework for studying intricate wave phenomena governed by nonlinearity and dispersion effects in three-dimensional physical space.
文摘Aiming at practical demands of manufacturing enterprises to the CAPP system in the Internet age, the CAPP model is presented based on Web and featured by open, universality and intelligence. A CAPP software package is developed with three layer structures （the database, the Web server and the client server） to realize CAPP online services. In the CAPP software package, a new process planning method called the successive casebased reasoning is presented. Using the method, process planning procedures are divided into three layers （the process planning, the process procedure and the process step）, which are treated with the successive process reasoning. Process planning rules can be regularly described due to the granularity-based rule classification. The CAPP software package combines CAPP software with online services. The process planning has the features of variant analogy and generative creation due to adopting the successive case-based reasoning, thus improving the universality and the practicability of the process planning.
文摘presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic consequence relation with the connective-free form can be represented by ADRFs.
基金The National Natural Science Foundation of China(No60403016),the Weaponry Equipment Foundation of PLA Equip-ment Ministry (No51406020105JB8103)
文摘The current extended fuzzy description logics lack reasoning algorithms with TBoxes. The problem of the satisfiability of the extended fuzzy description logic EFALC cut concepts w. r. t. TBoxes is proposed, and a reasoning algorithm is given. This algorithm is designed in the style of tableau algorithms, which is usually used in classical description logics. The transformation rules and the process of this algorithm is described and optimized with three main techniques： recursive procedure call, branch cutting and introducing sets of mesne results. The optimized algorithm is proved sound, complete and with an EXPTime complexity, and the satisfiability problem is EXPTime-complete.
