{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4NFARUZEWIF3JNNFSCUSIDRMN7","short_pith_number":"pith:4NFARUZE","schema_version":"1.0","canonical_sha256":"e34a08d324b20bb4b5a590a9240e2c6fe33be05d12c3eb8886c55fb9fd54027c","source":{"kind":"arxiv","id":"2503.00729","version":1},"attestation_state":"computed","paper":{"title":"CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ge Wang, Jinke Ren, Mingcong Lei, Qing Zhao, Shuguang Cui, Yao Guo, Yatong Han, Yiming Zhao, Zhen Li, Zhixin Mai","submitted_at":"2025-03-02T04:50:59Z","abstract_excerpt":"Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA) -- a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Int"},"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":"2503.00729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-02T04:50:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e329a6fd9d01a499bb8e37de528a09c920581e9f0112ce17e370401801c9d32d","abstract_canon_sha256":"8dc6ce184782d5589649d6c2e69db9ae2c74acd2594238ce98d378ed8a28a38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:28.282019Z","signature_b64":"s0rJddzkeUaMsurf0ltVvF9cwpgDdsNfo6rv9Un6oUsdhcNJIhNmBCTsVv/kHivk2e2bEmRYxPq8KNP2Z6z0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e34a08d324b20bb4b5a590a9240e2c6fe33be05d12c3eb8886c55fb9fd54027c","last_reissued_at":"2026-07-05T10:22:28.281460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:28.281460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ge Wang, Jinke Ren, Mingcong Lei, Qing Zhao, Shuguang Cui, Yao Guo, Yatong Han, Yiming Zhao, Zhen Li, Zhixin Mai","submitted_at":"2025-03-02T04:50:59Z","abstract_excerpt":"Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA) -- a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00729","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/2503.00729/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":"2503.00729","created_at":"2026-07-05T10:22:28.281530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00729v1","created_at":"2026-07-05T10:22:28.281530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00729","created_at":"2026-07-05T10:22:28.281530+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NFARUZEWIF3","created_at":"2026-07-05T10:22:28.281530+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NFARUZEWIF3JNNF","created_at":"2026-07-05T10:22:28.281530+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NFARUZE","created_at":"2026-07-05T10:22:28.281530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08169","citing_title":"CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7","json":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7.json","graph_json":"https://pith.science/api/pith-number/4NFARUZEWIF3JNNFSCUSIDRMN7/graph.json","events_json":"https://pith.science/api/pith-number/4NFARUZEWIF3JNNFSCUSIDRMN7/events.json","paper":"https://pith.science/paper/4NFARUZE"},"agent_actions":{"view_html":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7","download_json":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7.json","view_paper":"https://pith.science/paper/4NFARUZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00729&json=true","fetch_graph":"https://pith.science/api/pith-number/4NFARUZEWIF3JNNFSCUSIDRMN7/graph.json","fetch_events":"https://pith.science/api/pith-number/4NFARUZEWIF3JNNFSCUSIDRMN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7/action/storage_attestation","attest_author":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7/action/author_attestation","sign_citation":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7/action/citation_signature","submit_replication":"https://pith.science/pith/4NFARUZEWIF3JNNFSCUSIDRMN7/action/replication_record"}},"created_at":"2026-07-05T10:22:28.281530+00:00","updated_at":"2026-07-05T10:22:28.281530+00:00"}