Market & productsКоц: ИИ Palantir через Nebius мог получить данные россиянTechora.ru · 3dModellingAccelMPC: High-Rate, Low-Power FPGA-Accelerated Model Predictive Control for Tiny DronesarXiv — Systems and Control (eess.SY) · 4dDigital twinA Model-Centric DevOps Architecture for DEVS-Based Digital Twin Simulation ServicesarXiv API — полнотекстовый поиск "digital twin" · 4dDigital twinPlant Equivalent Controller Realizations for Attack-Resilient Cyber-Physical SystemsarXiv — Systems and Control (eess.SY) · 4dModellingIdentifiability of Latent Space Network Models on Anisotropic Thurston GeometriesarXiv — Physics and Society (physics.soc-ph) · 4dDigital twinОпубликованы итоги форсайт-сессии «Будущее безопасности киберфизических систем в России. Перспективы и векторы развития»spbIT · 4dForecastingBaseline-improved Economic Model Predictive Control for Optimal Microgrid DispatcharXiv — Systems and Control (eess.SY) · 4dModellingStochastic Model Predictive Control under AC Power-Flow Constraints Using Generative LearningarXiv — Systems and Control (eess.SY) · 5dMarket & productsPalantir меняет метрику: вместо количества клиентов — совокупная стоимость контрактовTechora.ru · 4dModellingАтаки на агентные системы и защита данныхХабр · 4dDigital twinEmbedding Model-form Uncertainty in Probabilistic Calibration of Digital Twins for BridgesarXiv API — полнотекстовый поиск "digital twin" · 4dModellingAgentHomeID - Agent-based modelling of building stock transformation: A multi-scale framework for policy assessment and infrastructure planningarXiv — Systems and Control (eess.SY) · 5d

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.