{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:37WZCYUZCY3XQDARNACSPOU7I2","short_pith_number":"pith:37WZCYUZ","schema_version":"1.0","canonical_sha256":"dfed9162991637780c11680527ba9f468e4e3bc636486af80a86f2252825e66b","source":{"kind":"arxiv","id":"2506.19160","version":1},"attestation_state":"computed","paper":{"title":"AgenticControl: An Automated Control Design Framework Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Mohammad Narimani, Seyyed Ali Emami","submitted_at":"2025-06-23T21:53:05Z","abstract_excerpt":"Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or uncertain dynamics. This paper introduces AgenticControl, a novel multi-agent framework that automates controller design using coordinated Large Language Model (LLM) agents. Through structured JSON communication, these agents handle tasks including controller selection, scenario design, parameter optimization, performance evaluation, and decision-making. Through an actor-critic optimization approach, the system iteratively improves performance while progressing through scena"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.19160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-23T21:53:05Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"6e3fb41f69626a2b384594caffe6f4069782b16841cc47963dc9606fadd21f9d","abstract_canon_sha256":"e17e03cf403aa86897ce981bbe2909d8163da888047e8a4000e2e6e9e96c0a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:10.117079Z","signature_b64":"7tI1YYfLjlf14ua2r4s69dpPsBiIbPjv62GUc46JoAKATRTsC17Yf1ToTwMn1bDib85952n6W78906wxLxP6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfed9162991637780c11680527ba9f468e4e3bc636486af80a86f2252825e66b","last_reissued_at":"2026-07-05T11:26:10.116300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:10.116300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgenticControl: An Automated Control Design Framework Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Mohammad Narimani, Seyyed Ali Emami","submitted_at":"2025-06-23T21:53:05Z","abstract_excerpt":"Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or uncertain dynamics. This paper introduces AgenticControl, a novel multi-agent framework that automates controller design using coordinated Large Language Model (LLM) agents. Through structured JSON communication, these agents handle tasks including controller selection, scenario design, parameter optimization, performance evaluation, and decision-making. Through an actor-critic optimization approach, the system iteratively improves performance while progressing through scena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19160","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.19160/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.19160","created_at":"2026-07-05T11:26:10.116413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19160v1","created_at":"2026-07-05T11:26:10.116413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19160","created_at":"2026-07-05T11:26:10.116413+00:00"},{"alias_kind":"pith_short_12","alias_value":"37WZCYUZCY3X","created_at":"2026-07-05T11:26:10.116413+00:00"},{"alias_kind":"pith_short_16","alias_value":"37WZCYUZCY3XQDAR","created_at":"2026-07-05T11:26:10.116413+00:00"},{"alias_kind":"pith_short_8","alias_value":"37WZCYUZ","created_at":"2026-07-05T11:26:10.116413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11015","citing_title":"Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2","json":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2.json","graph_json":"https://pith.science/api/pith-number/37WZCYUZCY3XQDARNACSPOU7I2/graph.json","events_json":"https://pith.science/api/pith-number/37WZCYUZCY3XQDARNACSPOU7I2/events.json","paper":"https://pith.science/paper/37WZCYUZ"},"agent_actions":{"view_html":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2","download_json":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2.json","view_paper":"https://pith.science/paper/37WZCYUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19160&json=true","fetch_graph":"https://pith.science/api/pith-number/37WZCYUZCY3XQDARNACSPOU7I2/graph.json","fetch_events":"https://pith.science/api/pith-number/37WZCYUZCY3XQDARNACSPOU7I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2/action/storage_attestation","attest_author":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2/action/author_attestation","sign_citation":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2/action/citation_signature","submit_replication":"https://pith.science/pith/37WZCYUZCY3XQDARNACSPOU7I2/action/replication_record"}},"created_at":"2026-07-05T11:26:10.116413+00:00","updated_at":"2026-07-05T11:26:10.116413+00:00"}