Active Inference-Enabled Agentic Closed-Loop ISAC with Long-Horizon Planning

2026-04-21

AI Summary

This work addresses the limited efficiency in existing closed-loop integrated sensing and communication (ISAC) systems, which stems from inadequate modeling of the coupling between perception and control. To overcome this, the study introduces active inference into closed-loop ISAC for the first time, proposing a factor graph-based wireless agent framework that jointly optimizes control policies and sensing resource allocation through forward–backward message passing. By integrating localization models with a channel knowledge graph, the framework constructs an uncertainty-aware digital twin to enable long-horizon planning. Simulations demonstrate that the proposed method adaptively schedules sensing resources according to spatially varying channel conditions, achieving a superior trade-off among tracking accuracy, control overhead, and sensing energy consumption compared to existing baselines.

Technology Category

• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Wireless agentic systems enable agents to autonomously perceive, reason, and act. However, existing works neglect the tight coupling between sensing and control in closed-loop integrated sensing and communication (ISAC) systems. In this paper, we propose an active inference (AIF)-driven wireless agentic system for closed-loop ISAC, which jointly optimizes control and sensing resource allocation via backward--forward message passing on a factor graph. The AIF agent maintains a generative model as a digital twin by integrating a localization model for uncertainty-aware state inference and a localization channel knowledge map (CKM) for approximating observation quality during planning. Simulation results demonstrate that the AIF-enabled agent adaptively allocates sensing resources based on spatially varying channel conditions, achieving superior balance among tracking accuracy, control effort, and sensing resource consumption over baseline strategies.

Problem

• Integrated Sensing and Communication
• Closed-loop ISAC
• Sensing-Control Coupling
• Wireless Agentic Systems
• Resource Allocation

Innovation

• Active Inference
• Integrated Sensing and Communication (ISAC)
• Factor Graph
• Digital Twin
• Channel Knowledge Map (CKM)