{"id":3634,"date":"2025-09-21T17:24:43","date_gmt":"2025-09-21T17:24:43","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3634"},"modified":"2025-09-21T17:24:43","modified_gmt":"2025-09-21T17:24:43","slug":"probabilistic-agentic-sweeps-for-rf-mode-recovery","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=3634","title":{"rendered":"Probabilistic Agentic Sweeps for RF Mode Recovery"},"content":{"rendered":"\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery-1.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery.\"><\/object><a id=\"wp-block-file--media-cc84a385-8826-4700-9a0e-6c9ae9ec3a9d\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery-1.pdf\">Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery-1.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-cc84a385-8826-4700-9a0e-6c9ae9ec3a9d\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Exploring the configuration space of radio frequency (RF) demodulation pipelines to find robust operating regimes<br>is challenging because simulation runs are computationally expensive and the response surface can contain sharp<br>failure boundaries. A na\u00efve uniform grid of experiments wastes resources by sampling regions where the response<br>is already well understood. In this paper we demonstrate a probabilistic, agentic sweep strategy using Gaussian<br>process (GP) surrogate models to adaptively select candidate points. The GP provides predictive mean and<br>uncertainty estimates that allow sampling to focus on regions where the model is both uncertain and near the<br>robustness threshold. Using a synthetic RF demodulation benchmark we show that GPguided sampling can<br>discover robust operating modes with far fewer evaluations than uniform sampling. Boundary heatmaps and<br>uncertainty maps illustrate how the surrogate model rapidly localises failure rims. Our results support the use of<br>probabilistic active learning for efficient robustness characterisation and RF mode recovery.<\/p>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery_Rev2.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery_Rev2.\"><\/object><a id=\"wp-block-file--media-4e15261f-2bdb-4cc0-bc1c-abd73e8c19e2\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery_Rev2.pdf\">Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery_Rev2<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/Probabilistic_Agentic_Sweeps_for_RF_Mode_Recovery_Rev2.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-4e15261f-2bdb-4cc0-bc1c-abd73e8c19e2\">Download<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Exploring the configuration space of radio frequency (RF) demodulation pipelines to find robust operating regimesis challenging because simulation runs are computationally expensive and the response surface can contain sharpfailure boundaries. A na\u00efve uniform grid of experiments wastes resources by sampling regions where the responseis already well understood. In this paper we demonstrate a probabilistic, agentic&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":47,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"class_list":["post-3634","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3634","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3634"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3634\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/47"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3634"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}