aiqbench analysis
This research introduces DSWM, a novel framework that applies decision-time planning and latent-space world modeling to optimize the repositioning of UAV base stations based on shifting traffic demand. By integrating a differentiable service simulator with an agentic controller, the system outperforms traditional optimization and reactive learning methods across multiple real-world datasets without relying solely on prediction accuracy. The work represents a significant advancement in applying advanced machine learning techniques to solve complex, dynamic problems within intelligent network architecture.
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
arXiv:2609.36845v1 Announce Type: cross Abstract: Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $\rho=0.95$. On a unified pipeline over three real datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.
Abstract:Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $\rho=0.95$. On a unified pipeline over three real datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.
13 pages, 13 figures, 4 tables, 2 algorithms. Submitted to IEEE Journal on Selected Areas in Communications (Special Issue on Agentic AI for Intelligent Networks)
Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2609.36845 [cs.NI]
(or arXiv:2609.36845v1 [cs.NI] for this version)
https://doi.org/10.48550/arXiv.2609.36845 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 271 words
Related coverage
FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling
arXiv · Jul 23, 2026
Presentation: From Hype to Strong Foundations: What the Rise, Fall and Resurgence of Agents Can Teach Us About Outlasting the Cycle
InfoQ · Jun 17, 2026
CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
arXiv · Jun 6, 2026
Cracking the Data Science Case Study Interview
Analytics Vidhya · Jul 26, 2026