Social Cognition Simulation With Large Language Model-Driven Agents,
2026
College of Politics, National Defense University, Shanghai 200433, China
Social Cognition Simulation With Large Language Model-Driven Agents, Mingxin Zhang, Jinxuan Wu, Rui Zhu, Yunlong Wang, Wenjuan Meng, Zhe Liu, Xu Li, Xiaolei Chen, Yuxuan Liang, Yi Zheng, Xiangyang Xue
Journal of System Simulation
Abstract: With the continuous evolution of the capabilities of generative LLMs, their application in social cognition simulation is demonstrating paradigm-shifting potential. Traditional social simulation methods predominantly rely on static rules and simplified behavioral models, making it difficult to capture the dynamic evolution and cultural complexity of human social behavior. LLM-driven agents, equipped with contextual understanding and natural language generation capabilities, are emerging as novel tools for modeling social cognitive mechanisms, enabling the simulation of complex sociopsychological processes such as identity construction, value judgment, and intentional reasoning. This paper briefly introduced the technical foundations of LLMs and highlighted their suitability for …
Integrated Development Environment For Digital Test Applications Based On Cloud-Edge-End Architecture,
2026
Beijing Institute of Tracking and Telecommunications Technology, Beijing 100094, China
Integrated Development Environment For Digital Test Applications Based On Cloud-Edge-End Architecture, Wenguang Yu, Qun Li, Hongjie Dang, Hao Chen, Ping Yang
Journal of System Simulation
Abstract: Digital test applications need to be constructed using the unified digital test development tool. After analyzing the features of digital test applications such as large-sample autonomous run, high computational efficiency requirement, and diverse task scenarios, this paper proposes the integrated development environment (IDE) for digital test applications based on cloud-edge-end architecture. The layered expandable architecture, the hybrid integration framework of multi-source heterogeneous models, and the cloud-edge-end collaborative deployment architecture are designed for the IDE of digital test applications. The IDE supports the rapid development, integration, and execution of digital test models and enables development of digital test applications on …
Research On Chain-Of-Thought Technology For Situational Awareness Based On Modular Reasoning,
2026
National Key Laboratory of Modeling and Simulation for Complex Systems, Beijing Simulation Center, Beijing 100854, China
Research On Chain-Of-Thought Technology For Situational Awareness Based On Modular Reasoning, Hongyuan Ji, Duzheng Qing
Journal of System Simulation
Abstract: To address issues such as insufficient intelligence of situational understanding in traditional simulation systems, a situational visual question answering dataset was constructed, and a modular reasoning framework was proposed. The SACoT was built, which, under a zero-shot setting, employed expert prompts to guide the model in task decomposition and multimodal information fusion, generating reasoning chains to enhance semantic cognition and interpretability and offering a scalable solution with low computation cost. Experimental results indicate that SACoT improves task allocation, enables models to focus on query-relevant image details, mitigates the fragmentation of chain-of-thought induced by multi-step reasoning, and reduces long-form …
Simulation Of Robotic Arm Ball-Catching Strategy Based On Curriculum Rl Of Transformer,
2026
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
Simulation Of Robotic Arm Ball-Catching Strategy Based On Curriculum Rl Of Transformer, Ziyao Zhang, Yunfeng Ji
Journal of System Simulation
Abstract: Method integrating the PPO algorithm with Transformer network architecture is proposed, and curriculum learning strategy is introduced to solve the difficult training convergence and low efficiency of traditional RL methods in complex and dynamic high-degree-of-freedom tasks such as robotic arm ball catching. The Transformer is employed to effectively capture the complex high-dimensional dependency between the robotic arm's state space, ball trajectory, and environmental physical parameters. Curriculum learning progressively increases catching difficulty by designing training tasks from simple to complex objectives. The experimental results show this method increases the ball-catching success rate by over 60% compared to the traditional …
Research On Uav Target Tracking Algorithm For Simulation Scenarios,
2026
School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou 450000, China
Research On Uav Target Tracking Algorithm For Simulation Scenarios, Xinyi Li, Zhenfei Wang, Han Wu
Journal of System Simulation
Abstract: To address the need for automatic UAV tracking of moving targets in simulated experiments, this paper proposed a long-term automatic tracking method based on an improved channel and spatial reliability-aware tracker (CSRT) algorithm. The target edge features were detected using the Laplacian of guided filter (LOGF) through guided filtering and then fused with the histogram of oriented gradient (HOG) and color names (CN) features to enhance the algorithm's discriminative ability for the target. To evaluate the target state, the paper used average peak correlation energy and perceptual hash Hamming distance. When the target was occluded, the paper employed YOLOv8 …
Distributed Optimization For Integrated Energy Based On Multi-Agent Reinforcement Learning,
2026
School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
Distributed Optimization For Integrated Energy Based On Multi-Agent Reinforcement Learning, Caixia Tao, Naikun Chen, Fengyang Gao, Jiangang Zhang
Journal of System Simulation
Abstract: To address the energy management and privacy preservation problems faced by the coordinated optimization of distributed integrated energy systems, a distributed coordinated optimization strategy based on the multi-agent proximal policy optimization algorithm was proposed. An energy management model was established under the MDP framework; the electrical and thermal heterogeneous energy characteristics were considered; a multi-region two-layer interaction mechanism was constructed. Under the framework of centralized training and decentralized execution, homomorphic encryption was utilized to avoid privacy leakage during the coordination process, while accurately quantifying individual contributions to mitigate the problem of variance explosion in multi-agent policy evaluation. In the …
Prediction Of Inflow Wind Field For Large-Scale Wind Turbines Based On Multimodal Hybrid Deep Learning,
2026
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Prediction Of Inflow Wind Field For Large-Scale Wind Turbines Based On Multimodal Hybrid Deep Learning, Jiheng Wang, Yang Hu, Ziqiu Song, Fang Fang, Jizhen Liu
Journal of System Simulation
Abstract: To address the demand for high-precision inflow wind field prediction in large-scale wind turbines, traditional CFD methods suffer from high computational costs and poor real-time applicability. This paper proposed a multimodal hybrid deep learning-based wind field prediction method. The proposed method took turbine operating parameters and far-range wind field images as inputs and generated short-range wind field images as outputs. By employing a U-Net-Transformer-GAN hybrid architecture, the model achieved multi-scale feature extraction, temporal dependency modeling, and highresolution wind field image generation. The vorticity transport equation and Kármán-Howarth turbulence statistics were incorporated as weak constraints to enhance physical consistency, while …
Llm-Driven Multi-Agent Social Network Simulation: Interdisciplinary Integration And Cutting-Edge Development,
2026
Academy of Military Science, Beijing 100097, China
Llm-Driven Multi-Agent Social Network Simulation: Interdisciplinary Integration And Cutting-Edge Development, Jiting Li, Yi Sun, Yirong Wang, Yiqin Lin, Jun Jia, Gangsong Ding
Journal of System Simulation
Abstract: The breakthrough of LLMs has provided powerful tools for social network research, advancing multi-agent social network simulation into a new era. This review systematically examined recent progress in LLM-driven multi-agent social network simulation research through a integrated perspective of multi-disciplines such as artificial intelligence, psychology, communication studies, and sociology. A three-tiered research system, which has gradually formed in this field and encompassed micro-level individual behaviors, meso-level interactive relations, and macro-level system emergence, was summarized. At the micro-level, research focuses on individual human behavior simulation, and numerous studies are dedicated to developing human-like agents with complex cognitive and affective architectures …
An Adaptive Robot Path Planning Based On Improved Rea* Algorithm,
2026
School of Mathematics and Statistics, Xidian University, Xi'an 710126, China
An Adaptive Robot Path Planning Based On Improved Rea* Algorithm, Ling Zhu, Jing Li, Zhaohui Zhang
Journal of System Simulation
Abstract: In order to improve the computational efficiency and path smoothness in a robot's global path planning, an adaptive robot path planning strategy based on an improved unilateral rectangle expansion A*(REA*) algorithm was proposed. The robot's operational safety was ensured by setting a buffer around obstacles. A passable interval formed by unilateral rectangle expansion was used as the operation unit, and bidirectional alternating search was combined to enhance the path planning efficiency. Inspired by potential field theory, the evaluation function was optimized by introducing a vector form to achieve fast adaptive obstacle avoidance. A new path planning strategy was proposed …
Evolutionary Game-Based Analysis Of Responses To Hallucinations In Generative Artificial Intelligence,
2026
School of Economics and Management of Beijing University of Posts and Telecommunications, Beijing 100876, China
Evolutionary Game-Based Analysis Of Responses To Hallucinations In Generative Artificial Intelligence, Qiang Yan, Qianyu Zhang, Na Wei
Journal of System Simulation
Abstract: The accelerated deployment of generative artificial intelligence, particularly large language models, has amplified the social risks of hallucinations, posing systemic threats to the credibility of the information ecosystem, the effectiveness of users’ cognitive decision-making, and the governance security in the public domain. Research primarily focuses on hallucination mitigation mechanisms at the technical level or the design of regulatory frameworks at the policy level, lacking a systematic theoretical analysis of the evolutionary logic of strategic interactions among the “large language models, users, and regulators” under conditions of bounded rationality. By introducing evolutionary game theory into the field of generative artificial …
Intelligent Air Combat Decision-Making Method Based On Bigru And Priority Dynamic Sampling,
2026
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
Intelligent Air Combat Decision-Making Method Based On Bigru And Priority Dynamic Sampling, Zhengkun Ding, Jiaqi Liu, Junzheng Xu, Yuezhu Xu, Xingmei Wang
Journal of System Simulation
Abstract: Current multi-agent reinforcement learning algorithms suffer from low efficiency in utilizing experience data and difficulties in setting appropriate learning rates. To address these issues, this paper proposed a BiGRU multi-agent PPO with priority sampling and dynamic learning rate. The algorithm incorporated a BiGRU network to enhance the policy network's ability to model temporal information. A priority partial sampling mechanism was introduced to improve the utilization efficiency of high-value experience data. Additionally, an improved Adam optimizer with dynamic learning rate adjustment was employed to address the challenge of learning rate configuration. Simulation experiment results demonstrate that the algorithm significantly …
Knowledge-Enhanced Llm-Based Method For Regional Traffic Signal Control,
2026
School of Artificial Intelligence, Anhui University, Hefei 230601, China
Knowledge-Enhanced Llm-Based Method For Regional Traffic Signal Control, Risheng Xu, Linyao Yang, Yuanqi Qin, Xiao Wang, Changyin Sun
Journal of System Simulation
Abstract: Adaptive traffic signal control (ATSC) is crucial for alleviating regional traffic congestion, yet it faces severe challenges in real-time response to unexpected events and global coordination. The DRL method relies on pure data-driven approaches, suffering from core limitations such as poor generalization, weak interpretability, and a lack of guidance from emergency disposal knowledge, which makes them difficult to meet the demands of complex traffic scenarios. A control system that integrates knowledge-driven and data-optimized approaches was proposed. The GraphRAG was used to construct a dynamic traffic knowledge graph, providing LLMs with real-time updated historical emergency disposal experience and road …
A Semantic Knowledge-Enhanced Assessment Method For Spectrum Effectiveness Of Low Earth Orbit Constellations,
2026
Joint Laboratory for Space Information Network Frequency and Orbit Technology and Applications, China Satellite Network System Research Institute Co., Ltd, Beijing 100000, China
A Semantic Knowledge-Enhanced Assessment Method For Spectrum Effectiveness Of Low Earth Orbit Constellations, Yiqing Liu, Qiuyang Zhang, Chunyu Liu, Yao Xue, Zhiwei Wei, Yan Feng
Journal of System Simulation
Abstract: In order to scientifically assess the spectrum effectiveness of low earth orbit constellations, the problems of insufficient adaptability of the traditional assessment framework and inaccurate estimation of KPIs under sparse data conditions were solved, a semantic knowledge-enhanced assessment method for spectrum effectiveness of low earth orbit constellations was proposed. A comprehensive multi-level, all band, and multi-dimensional spectrum effectiveness assessment framework covering link level, system level, geographical level, and service application level was constructed. A KPI intelligent prediction agent model integrating semantic knowledge and machine learning was proposed to quantify text-like design parameters using SentenceTransformer, so as to rapidly …
Simulation Method For Multi-Crew Construction Processes Based On Large Language Model-Powered Agent,
2026
College of Civil Engineering, Tongji University, Shanghai 200092, China
Simulation Method For Multi-Crew Construction Processes Based On Large Language Model-Powered Agent, Yifan Wang, Bin Yang, Congjun Wang
Journal of System Simulation
Abstract: Traditional construction simulation methods typically rely on predefined rules or static scheduling mechanisms, making it difficult to simulate interactive decision-making under complex constraints by dynamically adapting multi-crew construction scenarios. As a result, workforce idleness caused by process dependencies and spatial occupation fails to be solved. A simulation method for multicrew construction processes based on a LLM-powered agent was proposed. The distributed crew agents endowed with construction scenario understanding and reasoning capabilities were constructed, as well as a centralized project manager agent. A “single-manager and multiple-crew” decision-making mechanism for multi-agent interaction in construction was designed. Autonomous decision-making and coordination mechanism …
Resource-Efficient Continuous Learning Framework For Edge Real-Time Video Analytics,
2026
College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China; Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China
Resource-Efficient Continuous Learning Framework For Edge Real-Time Video Analytics, Shuxia Wu, Junjie Zhang, Delong Chen, Zheyi Chen
Journal of System Simulation
Abstract: By deploying lightweight models at the network edge, edge systems can provide services of real-time video analytics. However, due to the data drift caused by the discrepancy between model training and actual deployment, it is challenging to construct lightweight models that match real-world environments. To address this challenge, a resource-efficient continuous learning framework for edge real-time video analytics (CL4VA) was proposed. A region of interest-granularity predictor for accuracy degradation was introduced to efficiently select key samples from real-time video streams. A two-layer mixed sample pool was constructed to adaptively trigger the model's continuous learning and avoid the issue of …
Reinforcement Learning Based Method For Uav Team Orienteering Optimization Under Multi-Constraint Condition,
2026
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
Reinforcement Learning Based Method For Uav Team Orienteering Optimization Under Multi-Constraint Condition, Can Yang, Kai Chen, Feng Zhu
Journal of System Simulation
Abstract: Traditional optimization methods struggle with efficiency, while reinforcement learning approaches often yield low solution quality and high training costs. In response, this paper proposes an attention mechanism-based reinforcement learning method. A dynamic attention strategy network with multi-information fusion is designed to improve solution quality. A visibility-graph approach is employed to simplify threat zone constraints and speed up convergence, and a decoding sequence reordering mechanism is introduced for further performance optimization of the solution. The simulation results show that the method generates high-quality solutions within milliseconds, achieving total rewards that approach or even surpass those obtained by traditional solvers …
Strike Strategy Planning Method Of Unmanned Ground Vehicles Based On Improved Ppo Algorithm,
2026
Northwest Institute of Mechanical & Electrical Engineering, Xianyang 712099, China
Strike Strategy Planning Method Of Unmanned Ground Vehicles Based On Improved Ppo Algorithm, Bingkun Wang, Yue Wang, Mei Yang, Pengnian Zhang, Bohao Fan, Jie Tang
Journal of System Simulation
Abstract: An improved PPO algorithm based on the hybrid action space and gated recurrent unit (GRU) is proposed to address the limitations of predefined strike rules in maximizing the hitting accuracy of unmanned ground vehicles and the difficult coupling and optimization of continuous motion planning and discrete strike decision-making. The environmental model and target model are built for the process of unmanned ground vehicles' strike missions, coupled with a three-layer model for unmanned ground vehicles that fuses kinematic constraints, situational awareness, and dynamic decision-making. Two distinct policy networks are employed, including the continuous motion planning network for path planning, and …
Knowledge Closed-Loop Driving-Based Intelligent Game Confrontation Simulation,
2026
College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China; National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha 410073, China
Knowledge Closed-Loop Driving-Based Intelligent Game Confrontation Simulation, Quan Liu, Yu Wang, Linyue Liu, Hao Chen, Jian Huang
Journal of System Simulation
Abstract: For human-machine intelligence integration and collaborative intelligence enhancement, a “knowledge-model-data-knowledge” closed-loop paradigm for combat simulation is proposed to guide the design of a DRL-based game confrontation simulation architecture. By building a combat priori knowledge-guided DRL agent model, mining and analyzing the time series data of agent interactions generated during simulations, and extracting combat posterior knowledge that expands the cognition boundaries of commanders, the knowledge closed-loop driving mechanism for intelligent combat simulations is achieved. The experimental results indicate that the proposed mechanism can effectively endow the combat simulation system with intelligence growth capabilities, providing valuable reference for the deepening …
Intelligent Decision-Making Method In Imbalanced Air Combat Based On Asymmetric Self-Play,
2026
School of Software Engineering, Nanchang Hangkong University, Nanchang 330063, China
Intelligent Decision-Making Method In Imbalanced Air Combat Based On Asymmetric Self-Play, Wei Zheng, Jiahao Tang, Xiaoping Xiong, Xin Fan
Journal of System Simulation
Abstract: To solve the problem of strategy convergence caused by role homogenization in traditional self-play for imbalanced air combat, an intelligent decision-making method based on asymmetric selfplay was proposed. This method decoupled tactics from control by employing a hierarchical reinforcement learning framework and designed differentiated reward functions for advantaged and disadvantaged sides. Bidirectional independent policy pools were constructed to promote the co-evolution of strategies. The proximal policy optimization algorithm was utilized to train the model. Experiments in 1v1 weapon-imbalanced and 2v1 numerically-imbalanced scenarios demonstrate that compared to symmetric self-play, the proposed method increases the kill rate of the advantaged …
Agent-Based Pathfinding Method For Indoor Fire Emergency Evacuation,
2026
School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
Agent-Based Pathfinding Method For Indoor Fire Emergency Evacuation, Ao Tian, Jianqin Zhang, Zheng Wen, Chaonan Hu, Hong Zhao, Bo Shen
Journal of System Simulation
Abstract: To improve emergency evacuation efficiency and reduce casualties in dynamic fire scenarios, a real-time path re-planning method based on agents and dynamic A* algorithm framework is proposed. The behavior and actions of the agent is modeled. A reward function is designed, and an agent-based evacuation framework is constructed. Based on fire simulation data, a dynamic cost network involving parameters such as thermal radiation, smoke visibility, and CO concentration is constructed to achieve spatiotemporally continuous modeling of fire environments. By optimizing the composite cost function through dynamic weight allocation, combined with an improved heuristic function and dynamic search mechanism, local …
