Digital twinSchneider Electric pilots an AI data center digital twin in PortugalInvesting.com · 18hModellingLLM-Augmented Agent-Based Simulation of Cyber Social AgentsarXiv — Multiagent Systems (cs.MA) · yesterdayModellingBayesian inference for agent-based models with 90% fewer simulationsarXiv — Multiagent Systems (cs.MA) · yesterdayModellingAdapting neural posterior estimators for agent-based model inferencearXiv — Multiagent Systems (cs.MA) · yesterdayDigital twinModel-Free Generative Stealthy Attacks on Safety-Critical Vehicle Cyber-Physical SystemsarXiv — Systems and Control (eess.SY) · 2dDigital twinSchneider Electric, AVEVA, Nscale and Start Campus pilot AI digital twinEngineering.com · 5dDigital twinLarge Language Models Meet Bayesian Optimization: Towards Self-evolving Wireless Digital TwinsarXiv API — полнотекстовый поиск "digital twin" · 5dModellingJaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in SecondsarXiv — General Economics (econ.GN) · 6dDigital twinDigital Twins of Networked Dynamical Systems: Machine Learning Prediction of Synchronization Transitions in Coupled Chaotic OscillatorsarXiv API — полнотекстовый поиск "digital twin" · 6dDigital twinEvaluating Type-1 Diabetes Digital Twins by Decision QualityarXiv API — полнотекстовый поиск "digital twin" · 6dForecastingCertified Neural Approximation of Robust Nonlinear Model Predictive ControlarXiv — Systems and Control (eess.SY) · 6dForecastingIntegrating Flow Matching and Model Predictive Control for Safe Robot NavigationarXiv — Systems and Control (eess.SY) · 6d
Adapting neural posterior estimators for agent-based model inference
US & West ·
Agent-based models in economics and social sciences represent heterogeneous behavior and interactions through simulations, while their likelihood is often intractable for parameter estimation. The work examines likelihood-free neural inference, notably neural posterior estimation with normalizing flows providing amortized Bayesian inference. It notes that a pre-trained estimator may become inaccurate when the target task changes and discusses adapting such estimators.
Why it matters
It improves the robustness of calibrating large-scale agent-based models when task conditions change, which matters for applied forecasting.
arXiv:2610.32988v1 Announce Type: new Abstract: Social media bots are often portrayed as malicious automations to be detected and removed, but automation on social media platforms encompasses a wide spectrum of roles, behaviors, and rhetorical strategies that can shape online discourse in both…
The DF-NPE method combines learned time-series summaries with two conditional normalizing flows for synthetic-data generation and posterior estimation. It supplements direct simulations with synthetic training pairs and supports pooled and ordered training strategies. In two settings of the Brock-Hommes asset-pricing model it cuts direct simulations by 90% while achieving lower posterior discrepancy and runtime.
arXiv:2610.28907v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) offers a principled way of populating simulated economies with many heterogeneous decision makers.
