{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CWNBWH3QD2MBHSGWIIIOUC4GHV","short_pith_number":"pith:CWNBWH3Q","schema_version":"1.0","canonical_sha256":"159a1b1f701e9813c8d64210ea0b863d5e43c201b64c52138628e0cd7b8e06b6","source":{"kind":"arxiv","id":"2407.19094","version":6},"attestation_state":"computed","paper":{"title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bradly Stadie, Rui Shen, Zidan Wang","submitted_at":"2024-07-26T21:18:57Z","abstract_excerpt":"We introduce Wonderful Team, a multi-agent Vision Large Language Model (VLLM) framework for executing high-level robotic planning in a zero-shot regime. In our context, zero-shot high-level planning means that for a novel environment, we provide a VLLM with an image of the robot's surroundings and a task description, and the VLLM outputs the sequence of actions necessary for the robot to complete the task. Unlike previous methods for high-level visual planning for robotic manipulation, our method uses VLLMs for the entire planning process, enabling a more tightly integrated loop between percep"},"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":"2407.19094","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-26T21:18:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"fbcd266f5ac6968ea13adeed282b4af965c5a938a884379e0467d949ad9e345e","abstract_canon_sha256":"3e6cf4f68c06981358c50121ac86793d8173a76c0439c467749c34e40f637d53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:06.746375Z","signature_b64":"EC+pZmtv0e+Ch1xSEqGWKr8TfzSWk314qkeJGsha7ALIt73omWJUOFFVHpYtODv7WmYGVZjakUy2XQKBwCpyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159a1b1f701e9813c8d64210ea0b863d5e43c201b64c52138628e0cd7b8e06b6","last_reissued_at":"2026-07-05T10:09:06.745855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:06.745855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bradly Stadie, Rui Shen, Zidan Wang","submitted_at":"2024-07-26T21:18:57Z","abstract_excerpt":"We introduce Wonderful Team, a multi-agent Vision Large Language Model (VLLM) framework for executing high-level robotic planning in a zero-shot regime. In our context, zero-shot high-level planning means that for a novel environment, we provide a VLLM with an image of the robot's surroundings and a task description, and the VLLM outputs the sequence of actions necessary for the robot to complete the task. Unlike previous methods for high-level visual planning for robotic manipulation, our method uses VLLMs for the entire planning process, enabling a more tightly integrated loop between percep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19094","kind":"arxiv","version":6},"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/2407.19094/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":"2407.19094","created_at":"2026-07-05T10:09:06.745925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19094v6","created_at":"2026-07-05T10:09:06.745925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19094","created_at":"2026-07-05T10:09:06.745925+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWNBWH3QD2MB","created_at":"2026-07-05T10:09:06.745925+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWNBWH3QD2MBHSGW","created_at":"2026-07-05T10:09:06.745925+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWNBWH3Q","created_at":"2026-07-05T10:09:06.745925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15671","citing_title":"Long-Term Memory for VLA-based Agents in Open-World Task Execution","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV","json":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV.json","graph_json":"https://pith.science/api/pith-number/CWNBWH3QD2MBHSGWIIIOUC4GHV/graph.json","events_json":"https://pith.science/api/pith-number/CWNBWH3QD2MBHSGWIIIOUC4GHV/events.json","paper":"https://pith.science/paper/CWNBWH3Q"},"agent_actions":{"view_html":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV","download_json":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV.json","view_paper":"https://pith.science/paper/CWNBWH3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19094&json=true","fetch_graph":"https://pith.science/api/pith-number/CWNBWH3QD2MBHSGWIIIOUC4GHV/graph.json","fetch_events":"https://pith.science/api/pith-number/CWNBWH3QD2MBHSGWIIIOUC4GHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV/action/storage_attestation","attest_author":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV/action/author_attestation","sign_citation":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV/action/citation_signature","submit_replication":"https://pith.science/pith/CWNBWH3QD2MBHSGWIIIOUC4GHV/action/replication_record"}},"created_at":"2026-07-05T10:09:06.745925+00:00","updated_at":"2026-07-05T10:09:06.745925+00:00"}