World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI Systems

arXiv 2026 56.3 method

TLDR

Proposes a world-model-enabled causal digital twin framework for goal-oriented semantic communications in closed-loop physical AI systems.

Reasoning

The paper introduces a novel causal information value metric and uses world models for counterfactual reasoning and long-horizon rollouts, which is a strong theoretical contribution. However, the abstract lacks empirical validation or real-world experiments, and the connection to specific world model types like video or generative models is not explicit.

Read-first score

Read-first score 56.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 44.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%

91.1

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.9111553

Topical relevance 29%

62.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=evaluation,metric

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridge

Rank sensitivity

Stability: volatile; rank range: 432.

Keyword Scores

world model

model-based reinforcement learning world model

world dynamics prediction

world simulator

interactive world model

generative world model

video world model

Deep Analysis

Innovations

Causal information value (CIV) metric for evaluating marginal contribution of semantic tokens to long-term return via transmission interventions
World-model-enabled causal digital twin (WM-CDT) framework for closed-loop physical AI systems
Counterfactual reasoning for long-horizon imagined rollouts in semantic communications
Actor-critic policy training with high data efficiency for long-horizon agent control
Semantic token selector trained through CIV-per-bit evaluation

Methodology

The paper formulates semantic communications as a long-term return-per-bit maximization problem under wireless bit-budget constraints. It introduces a causal information value (CIV) metric and proposes a world-model-enabled causal digital twin (WM-CDT) framework that uses counterfactual reasoning for long-horizon rollouts to train an actor-critic policy and a semantic token selector. The framework is evaluated on an AirSim-Sionna-based UAV navigation simulator.

Key Results

Extensive simulations show that the proposed WM-CDT framework achieves significant improvement in return-per-kbit and navigation success rate compared to existing reinforcement learning solutions.

Resources

Paper