Digital twinHybrid Edge-Cloud Digital Twin for Poultry ControlarXiv — Systems and Control (eess.SY) · yesterdayModellingShared Control Between DRL and MPC for Multi-Class Transport NetworksarXiv — Systems and Control (eess.SY) · yesterdayDigital twinMulti-Viewpoint Modeling Framework for DT Integration with LLM AnalysisarXiv API — полнотекстовый поиск "digital twin" · 17hDigital twinStructured Persona Extraction for LLM-Based Digital TwinsarXiv — Computers and Society (cs.CY) · yesterdayForecastingLLM-Agent Stress Test: Feed Effects on Lexical DiversityarXiv — Multiagent Systems (cs.MA) · yesterdayModellingHow to manage behavior of multi-agent systemsХабр · yesterdayDigital twinDigital Twin for Ground-to-QEYSSat Quantum LinkarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinAligning Upper Ontologies for Defence: IES, HQDM, and BFOarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinReliability-Aware Scheduling for Digital Twin MaintenancearXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinAI disrupts glass fiber manufacturing: predictive maintenance, digital twins, and infrastructureGlobeNewswire · 3dDigital twinKMG implements digital twins at 12 fieldsdprom.kz — промышленность · 3dDigital twinDigital Twin of SWER Networks for Narrowband CommunicationarXiv API — полнотекстовый поиск "digital twin" · 4d
LLM-Agent Stress Test: Feed Effects on Lexical Diversity
US & West ·
A peer-voted social-platform testbed PV-SST is introduced to study population-level behavior of LLM agents. In a preregistered experiment with 448 trials, a feed of previous posts ranked by likes increased final-round lexical similarity, but no reliable advantage for distributed sources was found.
Why it matters
This work is important for understanding collective agent behavior and how social mechanisms can affect simulation outcomes.
The paper discusses sharing control authority between deep reinforcement learning (DRL) and model predictive control (MPC) for multi-class transportation networks. It aims to overcome limitations of each method: DRL's learning capacity in high-dimensional state spaces and MPC's computational cost.
A Monte Carlo-based simulator is developed for photon emission, transmission, and detection in the QEYSSat satellite quantum link. It probabilistically accounts for major physical effects, improving accuracy over analytical models.
A high-frequency digital twin of an operational SWER network was developed to test narrowband PLC communication. The model combines a segment-by-segment transmission line model with measurements of physical hardware, improving channel estimation accuracy. This allows assessing NB-PLC viability for grid upgrades.
