发表机构
University of Technology Sydney; University of Southern Queensland; The University of Sydney（悉尼科技大学; 南昆士兰大学; 悉尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出智能体语义感知闭环框架，通过因果Transformer和语义效用网络动态调整感知配置与时长，在Widar3.0上降低25.33%感知成本并保持85.79% Macro-F1，支持语义提前退出进一步节省资源。
AI 中文摘要
语义感知（SemS）获取与任务相关的信息，而非重建完整的物理信息。现有的语义感知公式通常以开环方式运行：感知配置和观测计划在推理前固定，无法响应不断演变的任务级证据。我们提出智能体语义感知（Agentic SemS），一种面向人工智能赋能的无线接入网络（AI-RANs）的闭环框架，在通信可行的配置集内控制感知。一个配置条件的因果Transformer从流式观测中更新语义信念，而键值缓存使得在配置变化时能够高效地更新状态，无需重复处理完整历史。一个语义效用网络在考虑感知成本后，估计在每个可行配置下获取下一个观测块的任务级收益。由此产生的延续效用共同支持下一个配置的选择和语义提前退出，使感知配置和持续时间适应不断演变的证据。预期的语义增益进一步与条件互信息相关联，为持续在线感知提供了信息价值解释。在Widar3.0上使用六种模拟感知配置进行的实验表明，与全序列High相比，资源高效的智能体设置将归一化累积感知成本降低了25.33%，同时实现了85.79%的Macro-F1。在相同的效用检查点，语义提前退出比无提前退出的自适应感知进一步降低了12.35%的成本，而Macro-F1仅下降了0.97个百分点。
英文摘要
Semantic sensing (SemS) acquires task-relevant information rather than reconstructing complete physical information. Existing SemS formulations typically operate open loop: sensing configurations and observation schedules are fixed before inference and cannot respond to evolving task-level evidence. We propose Agentic SemS, a closed-loop framework for AI-enabled radio access networks (AI-RANs) that controls sensing within a communication-feasible profile set. A profile-conditioned causal Transformer updates the semantic belief from streaming observations, while key-value caching enables efficient state updates across profile changes without repeatedly processing the complete history. A semantic utility network estimates the task-level benefit of acquiring the next observation block under each feasible profile after accounting for sensing cost. The resulting continuation utilities jointly support next-profile selection and semantic early exit, adapting sensing configuration and duration to evolving evidence. The expected semantic gain is further related to conditional mutual information, providing a value-of-information interpretation of continued online sensing. Experiments on Widar3.0 with six emulated sensing profiles show that, in comparison with full-sequence High, the resource-efficient Agentic setting reduces normalized cumulative sensing cost by 25.33% while achieving 85.79% Macro-F1. At the same utility checkpoint, semantic early exit provides a further 12.35% cost reduction over adaptive sensing without early exit, with a 0.97-percentage-point Macro-F1 decrease.
