发表机构
Digital Future Institute, Khalifa University; School of Information Science, Japan Institute of Science and Technology (JAIST); College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（数字未来研究所，哈利法大学; 信息科学学院，日本科学技术大学; 人工智能学院，南京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出RF-Agent，一种分层语言智能体控制架构，用于指令条件下的主动频谱感知，通过闭环监督和审计提升联合成功，实验显示在Core预算下显著优于基线。
AI 中文摘要
主动射频（RF）感知必须在接收器限制下获取证据，同时遵循确认、恢复和停止指令。我们提出RF-Agent，一种闭环架构，结合语言监督、情节记忆、确定性RF执行、感知反馈和基于证据的报告。一个独立的审计器检查轨迹合规性。我们推导了采集和监管请求界限，刻画了全历史令牌复杂度，并通过输出有效性和证据容量来界定联合成功。ActiveRF-AD在固定状态下测试指令变化，并评估联合成功，要求在同一情节中同时满足合规性和RF正确性。在共享感知状态下对不同指令进行训练，将反事实对准确率从24.03%提高到96.22%，并将Core联合成功从65.13%提高到72.12%。在6.99个百分点的联合成功提升中，6.73个百分点反映了所有情节中RF正确但不合规的比例下降。在Core预算为3时，配对训练的分层控制达到66.60%的联合成功，而直接动作控制仅为9.17%。在相同预算下的另一项比较中，RF-Agent相对于初始状态规划器，联合成功提高了2.31个百分点，并将RF采集减少了12.3%，但推理成本增加。跨骨干诊断涵盖三个模型系列。这些结果表明，指令响应式控制能提高任务完成度，这超出了仅通过RF准确性所能揭示的范围。
英文摘要
Active radio-frequency (RF) sensing must acquire evidence under receiver limits while following confirmation, recovery, and stopping instructions. \newhl{We propose RF-Agent, a closed-loop architecture combining language supervision, episode memory, deterministic RF execution, perception feedback, and evidence-based reporting.} An independent auditor checks trajectory compliance. We derive acquisition and supervisory-request bounds, characterize full-history token complexity, and bound joint success by output validity and evidence capacity. \newhl{ActiveRF-AD tests instruction changes at fixed states and evaluates joint success, requiring compliance and RF correctness in the same episode.} \newhl{Training on different instructions at shared sensing states raises counterfactual-pair accuracy from 24.03\% to 96.22\% and Core joint success from 65.13\% to 72.12\%. Of the 6.99-point joint-success gain, 6.73 points reflect a decrease in the fraction of all episodes that are RF-correct but noncompliant.} \newhl{At Core budget three, paired-training hierarchical control achieves 66.60\% joint success versus 9.17\% for direct-action control.} \newhl{In a separate comparison at the same budget, RF-Agent improves joint success by 2.31 points and reduces RF acquisitions by 12.3\% relative to an initial-state planner, at increased inference cost.} Cross-backbone diagnostics cover three model families. These results show how instruction-responsive control improves task completion beyond what RF accuracy alone reveals.
