# Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning

arXiv: https://arxiv.org/abs/2511.02748 · HTML: https://mlsanity.com/paper/2511.02748/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agentic AI for wireless networks](https://mlsanity.com/agents/agentic-ai-for-wireless-networks/)

## Builds on (most cited first, 14 of 14)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges](https://mlsanity.com/paper/2510.13654/) (2025)
- [World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks](https://mlsanity.com/paper/2506.00417/) (2025)
- [Understanding Physical Dynamics with Counterfactual World Modeling](https://mlsanity.com/paper/2312.06721/) (2023)
- [Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting](https://mlsanity.com/paper/2509.24789/) (2025)
- [Intent-Based Network for RAN Management with Large Language Models](https://mlsanity.com/paper/2507.14230/) (2025)
- [Generalized Kullback-Leibler Divergence Loss](https://mlsanity.com/paper/2503.08038/) (2025)
- [LLM-hRIC: LLM-empowered Hierarchical RAN Intelligent Control for O-RAN](https://mlsanity.com/paper/2504.18062/) (2025)
- [Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN](https://mlsanity.com/paper/2510.05255/) (2025)
- [An Experimental Reservoir-Augmented Foundation Model: 6G O-RAN Case Study](https://mlsanity.com/paper/2508.07778/) (2025)
- [Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges](https://mlsanity.com/paper/2508.09561/) (2025)
- [Sample-Efficient and Smooth Cross-Entropy Method Model Predictive Control Using Deterministic Samples](https://mlsanity.com/paper/2510.05706/) (2025)

## Built on by (most cited first, 4 of 4)

- [LLM-Based Agentic Negotiation for 6G: Addressing Uncertainty Neglect and Tail-Event Risk](https://mlsanity.com/paper/2511.19175/) (2025)
- [Digital Co-Founders: Transforming Imagination into Viable Solo Business via Agentic AI](https://mlsanity.com/paper/2511.09533/) (2025)
- [LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G](https://mlsanity.com/paper/2601.12375/) (2026)
- [Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks](https://mlsanity.com/paper/2606.18272/) (2026)

## Abstract (arXiv)

We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond large language models (LLMs) as the primary modeling primitive. Actions such as physical resource blocks (PRBs) are treated as first-class control inputs in a causal world model, and both aleatoric and epistemic uncertainty are modeled for prediction and what-if analysis. An agentic, model predictive control (MPC)-based cross-entropy method (CEM) planner operates over short horizons, using prior-mean rollouts within data-driven PRB bounds to maximize a deterministic reward. The model couples multi-scale structured state-space mixtures (MS3M) with a compact stochastic latent to form WM-MS3M, summarizing key performance indicators (KPIs) histories and predicting next-step KPIs under hypothetical PRB sequences. On realistic O-RAN traces, WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference, enabling rare-event simulation and offline policy screening.