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
Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture th...Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues.Unlike centralized approaches,In-Mig performs reasoning in situ,ensuring that raw data remains within institutional boundaries while allowing for cross-venue synthesis.The architecture features a policy-scoped memory model,utility-driven route planning,and cryptographic trust enforcement.Aprototype using JADE for mobility and quantizedMistral-7B demonstrates practical feasibility.Evaluation across various scenarios shows that In-Mig achieves 92%similarity to centralized baselines,confirming its utility and strong privacy guarantees.These results suggest that migrating,privacy-preserving LLM agents can effectively support decentralized reasoning in trust-sensitive domains.展开更多
The novel concept of Compound-Agent is proposed,which consists of some independent sub-agents that share common beliefs and employ community actions. The Explicit Model of Coordination, which is used in the coordinati...The novel concept of Compound-Agent is proposed,which consists of some independent sub-agents that share common beliefs and employ community actions. The Explicit Model of Coordination, which is used in the coordination of the sub-agents of Compound-Agent, is provided. The actions of each sub-agent are rule-based determined, and the rule base can be adjusted on time.The approximate fuzzy reasoning is used to improve the speed of learn and reduce the number of rules, which makes Compound-Agent suitable for real time and dynamic applications. A real application, the design of the control system of flat-knitting machine employing the concept of Compound- Agent, is discussed briefly.展开更多
Small Language Models offer an efficient alternative for structured information extraction.We present SLM-MATRIX,a multi-path collaborative reasoning and verification framework based on SLMs,designed to extract materi...Small Language Models offer an efficient alternative for structured information extraction.We present SLM-MATRIX,a multi-path collaborative reasoning and verification framework based on SLMs,designed to extract material names,numerical values,and physical units from materials science literature.The framework integrates three complementary reasoning paths:a multi-agent collaborative path,a generator–discriminator path,and a dual cross-verification path.SLM-MATRIX achieves an accuracy of 92.85%on the BulkModulus dataset and reaches 77.68%accuracy on the MatSynTriplet dataset,both outperforming conventional methods and single-pathmodels.Moreover,experiments on general reasoning benchmarks such as GSM8K and SVAMP validate the framework’s strong generalization capability.Ablation studies evaluate the effects of agent number,Mixture-of-Agents(MoA)depth,and discriminator design on overall performance.Overall,SLM-MATRIX presents an effective approach for high-quality material information extraction in resource-constrained and offers new insights into structured scientific text understanding tasks.展开更多
Large language models(LLMs)have emerged as transformative tools with significant potential across healthcare and medicine.In clinical settings,they hold promises for tasks ranging from clinical decision support to pat...Large language models(LLMs)have emerged as transformative tools with significant potential across healthcare and medicine.In clinical settings,they hold promises for tasks ranging from clinical decision support to patient education.Advances in LLM agents further broaden their utility by enabling multimodal processing and multi-task handling in complex clinical workflows.However,evaluating the performance of LLMs in medical contexts presents unique challenges due to the high-risk nature of healthcare and the complexity of medical data.This paper provides a comprehensive overview of current evaluation practices for LLMs and LLM agents in medicine.We contributed 3 main aspects:First,we summarized data sources used in evaluations,including existing medical resources and manually designed clinical questions,offering a basis for LLM evaluation in medical settings.Second,we analyzed key medical task scenarios:closed-ended tasks,open-ended tasks,image processing tasks,and real-world multitask scenarios involving LLM agents,thereby offering guidance for further research across different medical applications.Third,we compared evaluation methods and dimensions,covering both automated metrics and human expert assessments,while addressing traditional accuracy measures alongside agent-specific dimensions,such as tool usage and reasoning capabilities.Finally,we identified key challenges and opportunities in this evolving field,emphasizing the need for continued research and interdisciplinary collaboration between healthcare professionals and computer scientists to ensure safe,ethical,and effective deployment of LLMs in clinical practice.展开更多
DeepSeek自2025年1月发布以来,凭借其较强的推理能力、混合专家模型MoE(Mixture of Experts)、门控机制等创新技术,以及算力要求和训练成本的降低,吸引了亚马逊、微软、百度、腾讯等国内外科技企业和海尔、美的、海信、TCL等头部家电企...DeepSeek自2025年1月发布以来,凭借其较强的推理能力、混合专家模型MoE(Mixture of Experts)、门控机制等创新技术,以及算力要求和训练成本的降低,吸引了亚马逊、微软、百度、腾讯等国内外科技企业和海尔、美的、海信、TCL等头部家电企业纷纷接入DeepSeek大模型,使得普通百姓享受到了DeepSeek给生活和工作带来的便利,具备了从用户拉动基于DeepSeek推理大模型的智能家电智能体的基础,为解决智能家电用户体验不佳、市场销售不及预期的问题提供了新的方案。因此,研究DeepSeek的运行机理和智能家电智能体的架构,从问题边界、知识库构建、人机交互界面等方面研究基于DeepSeek推理大模型的智能家电智能体使用技术路线及应用,期望加速DeepSeek在智能家电行业的应用,提升用户使用体验的满意度,为家电行业的智能化转型提供一种新的思路。展开更多
针对复杂战场环境下大模型(large language models,LLMs)态势预测与决策能力不足的问题,以人脑预演理论为核心出发点,提出一种融合预演机制与反事实反思的大模型作战决策方法。预演驱动的态势预测,结合军事常识、武器参数及态势推演路...针对复杂战场环境下大模型(large language models,LLMs)态势预测与决策能力不足的问题,以人脑预演理论为核心出发点,提出一种融合预演机制与反事实反思的大模型作战决策方法。预演驱动的态势预测,结合军事常识、武器参数及态势推演路径混合全参微调,使大模型基于当前战场态势生成高置信度的未来态势预测结果;反事实反思的决策优化,针对备选决策模拟“未执行该决策”的反事实场景,对比“执行-未执行”的因果差异生成包含“风险-收益”权衡的综合决策。在两栖登陆想定中的仿真实验表明:该方法显著提升大模型的态势预测能力与作战决策水平,通过融合预演理论与反事实反思,有效增强了大模型在复杂战场中的决策效能,为智能指挥决策系统提供了新路径。展开更多
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.
文摘Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues.Unlike centralized approaches,In-Mig performs reasoning in situ,ensuring that raw data remains within institutional boundaries while allowing for cross-venue synthesis.The architecture features a policy-scoped memory model,utility-driven route planning,and cryptographic trust enforcement.Aprototype using JADE for mobility and quantizedMistral-7B demonstrates practical feasibility.Evaluation across various scenarios shows that In-Mig achieves 92%similarity to centralized baselines,confirming its utility and strong privacy guarantees.These results suggest that migrating,privacy-preserving LLM agents can effectively support decentralized reasoning in trust-sensitive domains.
文摘The novel concept of Compound-Agent is proposed,which consists of some independent sub-agents that share common beliefs and employ community actions. The Explicit Model of Coordination, which is used in the coordination of the sub-agents of Compound-Agent, is provided. The actions of each sub-agent are rule-based determined, and the rule base can be adjusted on time.The approximate fuzzy reasoning is used to improve the speed of learn and reduce the number of rules, which makes Compound-Agent suitable for real time and dynamic applications. A real application, the design of the control system of flat-knitting machine employing the concept of Compound- Agent, is discussed briefly.
文摘Small Language Models offer an efficient alternative for structured information extraction.We present SLM-MATRIX,a multi-path collaborative reasoning and verification framework based on SLMs,designed to extract material names,numerical values,and physical units from materials science literature.The framework integrates three complementary reasoning paths:a multi-agent collaborative path,a generator–discriminator path,and a dual cross-verification path.SLM-MATRIX achieves an accuracy of 92.85%on the BulkModulus dataset and reaches 77.68%accuracy on the MatSynTriplet dataset,both outperforming conventional methods and single-pathmodels.Moreover,experiments on general reasoning benchmarks such as GSM8K and SVAMP validate the framework’s strong generalization capability.Ablation studies evaluate the effects of agent number,Mixture-of-Agents(MoA)depth,and discriminator design on overall performance.Overall,SLM-MATRIX presents an effective approach for high-quality material information extraction in resource-constrained and offers new insights into structured scientific text understanding tasks.
基金supported by the Start-up Fund for RAPs under the Strategic Hiring Scheme(Grant No.P0048623)from HKSARthe Global STEM Professorship Scheme(Grant No.P0046113)。
文摘Large language models(LLMs)have emerged as transformative tools with significant potential across healthcare and medicine.In clinical settings,they hold promises for tasks ranging from clinical decision support to patient education.Advances in LLM agents further broaden their utility by enabling multimodal processing and multi-task handling in complex clinical workflows.However,evaluating the performance of LLMs in medical contexts presents unique challenges due to the high-risk nature of healthcare and the complexity of medical data.This paper provides a comprehensive overview of current evaluation practices for LLMs and LLM agents in medicine.We contributed 3 main aspects:First,we summarized data sources used in evaluations,including existing medical resources and manually designed clinical questions,offering a basis for LLM evaluation in medical settings.Second,we analyzed key medical task scenarios:closed-ended tasks,open-ended tasks,image processing tasks,and real-world multitask scenarios involving LLM agents,thereby offering guidance for further research across different medical applications.Third,we compared evaluation methods and dimensions,covering both automated metrics and human expert assessments,while addressing traditional accuracy measures alongside agent-specific dimensions,such as tool usage and reasoning capabilities.Finally,we identified key challenges and opportunities in this evolving field,emphasizing the need for continued research and interdisciplinary collaboration between healthcare professionals and computer scientists to ensure safe,ethical,and effective deployment of LLMs in clinical practice.
文摘DeepSeek自2025年1月发布以来,凭借其较强的推理能力、混合专家模型MoE(Mixture of Experts)、门控机制等创新技术,以及算力要求和训练成本的降低,吸引了亚马逊、微软、百度、腾讯等国内外科技企业和海尔、美的、海信、TCL等头部家电企业纷纷接入DeepSeek大模型,使得普通百姓享受到了DeepSeek给生活和工作带来的便利,具备了从用户拉动基于DeepSeek推理大模型的智能家电智能体的基础,为解决智能家电用户体验不佳、市场销售不及预期的问题提供了新的方案。因此,研究DeepSeek的运行机理和智能家电智能体的架构,从问题边界、知识库构建、人机交互界面等方面研究基于DeepSeek推理大模型的智能家电智能体使用技术路线及应用,期望加速DeepSeek在智能家电行业的应用,提升用户使用体验的满意度,为家电行业的智能化转型提供一种新的思路。
文摘针对复杂战场环境下大模型(large language models,LLMs)态势预测与决策能力不足的问题,以人脑预演理论为核心出发点,提出一种融合预演机制与反事实反思的大模型作战决策方法。预演驱动的态势预测,结合军事常识、武器参数及态势推演路径混合全参微调,使大模型基于当前战场态势生成高置信度的未来态势预测结果;反事实反思的决策优化,针对备选决策模拟“未执行该决策”的反事实场景,对比“执行-未执行”的因果差异生成包含“风险-收益”权衡的综合决策。在两栖登陆想定中的仿真实验表明:该方法显著提升大模型的态势预测能力与作战决策水平,通过融合预演理论与反事实反思,有效增强了大模型在复杂战场中的决策效能,为智能指挥决策系统提供了新路径。
