{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4LVS3ISFV7F3ISUPFPMBYQ7ZMJ","short_pith_number":"pith:4LVS3ISF","schema_version":"1.0","canonical_sha256":"e2eb2da245afcbb44a8f2bd81c43f9626354bee857091e103702e75304085c52","source":{"kind":"arxiv","id":"2503.08302","version":1},"attestation_state":"computed","paper":{"title":"General-Purpose Aerial Intelligent Agents Empowered by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ji Zhao, Xiao Lin","submitted_at":"2025-03-11T11:13:58Z","abstract_excerpt":"The emergence of large language models (LLMs) opens new frontiers for unmanned aerial vehicle (UAVs), yet existing systems remain confined to predefined tasks due to hardware-software co-design challenges. This paper presents the first aerial intelligent agent capable of open-world task execution through tight integration of LLM-based reasoning and robotic autonomy. Our hardware-software co-designed system addresses two fundamental limitations: (1) Onboard LLM operation via an edge-optimized computing platform, achieving 5-6 tokens/sec inference for 14B-parameter models at 220W peak power; (2)"},"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":"2503.08302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-11T11:13:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f4d89ba27de75e3a50676e0f4d9f7784c69981dc20b6e58a8af694dc78223b4","abstract_canon_sha256":"1cd86f1fc6315d2b5d5125ac68a968d220f730492a7807a4c4586f67a4e5da93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:56.183592Z","signature_b64":"poBMkDJoq3rqsCfIhwuQmcYip7VKH6FwJVprIbGW06/KRuBTfFqnvegH50jyhMIN31jZhqK1zcWqiZBli9wGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2eb2da245afcbb44a8f2bd81c43f9626354bee857091e103702e75304085c52","last_reissued_at":"2026-07-05T10:28:56.182577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:56.182577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General-Purpose Aerial Intelligent Agents Empowered by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ji Zhao, Xiao Lin","submitted_at":"2025-03-11T11:13:58Z","abstract_excerpt":"The emergence of large language models (LLMs) opens new frontiers for unmanned aerial vehicle (UAVs), yet existing systems remain confined to predefined tasks due to hardware-software co-design challenges. This paper presents the first aerial intelligent agent capable of open-world task execution through tight integration of LLM-based reasoning and robotic autonomy. Our hardware-software co-designed system addresses two fundamental limitations: (1) Onboard LLM operation via an edge-optimized computing platform, achieving 5-6 tokens/sec inference for 14B-parameter models at 220W peak power; (2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08302","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/2503.08302/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":"2503.08302","created_at":"2026-07-05T10:28:56.182710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08302v1","created_at":"2026-07-05T10:28:56.182710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08302","created_at":"2026-07-05T10:28:56.182710+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LVS3ISFV7F3","created_at":"2026-07-05T10:28:56.182710+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LVS3ISFV7F3ISUP","created_at":"2026-07-05T10:28:56.182710+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LVS3ISF","created_at":"2026-07-05T10:28:56.182710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.10605","citing_title":"LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15486","citing_title":"A Universal Large Language Model -- Drone Command and Control Interface","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":182,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ","json":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ.json","graph_json":"https://pith.science/api/pith-number/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/graph.json","events_json":"https://pith.science/api/pith-number/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/events.json","paper":"https://pith.science/paper/4LVS3ISF"},"agent_actions":{"view_html":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ","download_json":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ.json","view_paper":"https://pith.science/paper/4LVS3ISF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08302&json=true","fetch_graph":"https://pith.science/api/pith-number/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/action/storage_attestation","attest_author":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/action/author_attestation","sign_citation":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/action/citation_signature","submit_replication":"https://pith.science/pith/4LVS3ISFV7F3ISUPFPMBYQ7ZMJ/action/replication_record"}},"created_at":"2026-07-05T10:28:56.182710+00:00","updated_at":"2026-07-05T10:28:56.182710+00:00"}