Digital twinJanus: One Agent, Two Roles for Digital Twin Construction and Network OrchestrationarXiv API — полнотекстовый поиск "digital twin" · 2dModellingStochastic MPC robust to errors in disturbance statisticsarXiv — Systems and Control (eess.SY) · 2dModellingРоман Венедиктов («Эмерджентные мультиагентные системы»): «Сегодня сам факт использования ИИ стал обычной частью корпоративной ИТ-среды»spbIT · 2dDigital twinA High-Fidelity Cardiac Digital Twin for Assessing Rate-Dependent Responses: A Comparative Multi-scale Study of TT2 and Tomek Models in Stratified 3D VentriclesarXiv API — полнотекстовый поиск "digital twin" · 2dForecastingAdaptive clustering for robust distributed MPC of coupled multi-agent systemsarXiv — Systems and Control (eess.SY) · 2dForecastingNeural approximation of NMPC without expert demonstrationsarXiv — Systems and Control (eess.SY) · 2dAssets & dataAn operational model for a trusted data space in vocational educationarXiv — Computers and Society (cs.CY) · 2dModellingАгентная система для тех, кто вкатывается: собираем агента поддержки от одного файла до Temporal, саги и circuit breakerХабр · 3dDigital twinOnline digital twin: data assimilation and control in a mean-field formulationarXiv — Systems and Control (eess.SY) · 3dDigital twinSurvey of digital twin networks for 6G: architecture, technologies and AI controlarXiv — Systems and Control (eess.SY) · 3dDigital twin5G NR neural receiver trained on corridor digital twin dataarXiv API — полнотекстовый поиск "digital twin" · 3dForecastingSampling-based MPC unified as a single sequential Monte Carlo algorithmarXiv — Systems and Control (eess.SY) · 3d

LLM-Agent Stress Test: Feed Effects on Lexical Diversity

US & West · 24 Aug

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.

Relevant to DT products

Original headline: Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources

Read the original: arXiv — Multiagent Systems (cs.MA)

Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.