{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2YFEJLUEZ3HVDHPQT4TZDWYGT","short_pith_number":"pith:Q2YFEJLU","schema_version":"1.0","canonical_sha256":"86b052257426767a8cef84f93c8ed834c1130eda0feb288979cd8e88fc97914b","source":{"kind":"arxiv","id":"2409.10444","version":3},"attestation_state":"computed","paper":{"title":"LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abdalla Swikir, Fan Wu, Jicong Ao, Sami Haddadin, Yansong Wu","submitted_at":"2024-09-16T16:28:34Z","abstract_excerpt":"Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually can be effort-intensive. Large language models (LLMs) have recently been applied to robotic task planning for generating action sequences, yet their ability to generate BTs has not been fully investigated. To this end, we propose LLM-as-BT-Planner, a novel framework that leverages LLMs for BT generation in robotic assembly task planning. Four in-context lear"},"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":"2409.10444","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-16T16:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"10e933b913c39d79c3e4f9a98028159843569c177940b186601d63430b553280","abstract_canon_sha256":"28b264bb0956faf85817766970d8cead32eec4bbf7e560d077f309dd819207d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:18.294152Z","signature_b64":"X6S9RQknN2Tp9U29NaPOGOtoQwCJwXdzWRq6JKrIhbA0WuNaGizBnrbZXwH7DZ7QDt5RtdHAx+0zkTSRGGWQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b052257426767a8cef84f93c8ed834c1130eda0feb288979cd8e88fc97914b","last_reissued_at":"2026-07-05T11:23:18.293625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:18.293625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abdalla Swikir, Fan Wu, Jicong Ao, Sami Haddadin, Yansong Wu","submitted_at":"2024-09-16T16:28:34Z","abstract_excerpt":"Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually can be effort-intensive. Large language models (LLMs) have recently been applied to robotic task planning for generating action sequences, yet their ability to generate BTs has not been fully investigated. To this end, we propose LLM-as-BT-Planner, a novel framework that leverages LLMs for BT generation in robotic assembly task planning. Four in-context lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10444","kind":"arxiv","version":3},"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/2409.10444/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":"2409.10444","created_at":"2026-07-05T11:23:18.293694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10444v3","created_at":"2026-07-05T11:23:18.293694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10444","created_at":"2026-07-05T11:23:18.293694+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2YFEJLUEZ3H","created_at":"2026-07-05T11:23:18.293694+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2YFEJLUEZ3HVDHP","created_at":"2026-07-05T11:23:18.293694+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2YFEJLU","created_at":"2026-07-05T11:23:18.293694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30613","citing_title":"Sequential Planning via Anchored Robotic Keypoints","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12358","citing_title":"From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT","json":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT.json","graph_json":"https://pith.science/api/pith-number/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/graph.json","events_json":"https://pith.science/api/pith-number/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/events.json","paper":"https://pith.science/paper/Q2YFEJLU"},"agent_actions":{"view_html":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT","download_json":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT.json","view_paper":"https://pith.science/paper/Q2YFEJLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10444&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/action/storage_attestation","attest_author":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/action/author_attestation","sign_citation":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/action/citation_signature","submit_replication":"https://pith.science/pith/Q2YFEJLUEZ3HVDHPQT4TZDWYGT/action/replication_record"}},"created_at":"2026-07-05T11:23:18.293694+00:00","updated_at":"2026-07-05T11:23:18.293694+00:00"}