{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NUSO4L65BSL7USTP27LBZRLVS6","short_pith_number":"pith:NUSO4L65","schema_version":"1.0","canonical_sha256":"6d24ee2fdd0c97fa4a6fd7d61cc575979504d107577cfc0d68773ad5309873fa","source":{"kind":"arxiv","id":"2311.05997","version":3},"attestation_state":"computed","paper":{"title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anji Liu, Bowei Zhang, Haowei Lin, Jinbing Hou, Shaofei Cai, Xiaojian Ma, Yaodong Yang, Yitao Liang, Yonggang Jin, Zhaofeng He, Zihao Wang, Zilong Zheng","submitted_at":"2023-11-10T11:17:58Z","abstract_excerpt":"Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all withi"},"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":"2311.05997","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-10T11:17:58Z","cross_cats_sorted":[],"title_canon_sha256":"4620623b9689c314298b176567663fc337d2519a79d85bf23ebb4bf73876270b","abstract_canon_sha256":"15a24a65d068b20e3767843c4298625aeb367d935f73e11d0435f38e57f57360"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:31.492764Z","signature_b64":"nm1SZAa0O+PaEQEYzeVrHpDkh2donF2sl8h0e5YTK+iuLZu60JTfKbfCxbO6Dx0yk+u4stjHt4noH6V+J+DCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d24ee2fdd0c97fa4a6fd7d61cc575979504d107577cfc0d68773ad5309873fa","last_reissued_at":"2026-07-05T07:18:31.492203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:31.492203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anji Liu, Bowei Zhang, Haowei Lin, Jinbing Hou, Shaofei Cai, Xiaojian Ma, Yaodong Yang, Yitao Liang, Yonggang Jin, Zhaofeng He, Zihao Wang, Zilong Zheng","submitted_at":"2023-11-10T11:17:58Z","abstract_excerpt":"Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all withi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05997","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/2311.05997/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":"2311.05997","created_at":"2026-07-05T07:18:31.492273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05997v3","created_at":"2026-07-05T07:18:31.492273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05997","created_at":"2026-07-05T07:18:31.492273+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUSO4L65BSL7","created_at":"2026-07-05T07:18:31.492273+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUSO4L65BSL7USTP","created_at":"2026-07-05T07:18:31.492273+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUSO4L65","created_at":"2026-07-05T07:18:31.492273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02125","citing_title":"Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18636","citing_title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13771","citing_title":"AppAgent: Multimodal Agents as Smartphone Users","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22847","citing_title":"Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07429","citing_title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6","json":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6.json","graph_json":"https://pith.science/api/pith-number/NUSO4L65BSL7USTP27LBZRLVS6/graph.json","events_json":"https://pith.science/api/pith-number/NUSO4L65BSL7USTP27LBZRLVS6/events.json","paper":"https://pith.science/paper/NUSO4L65"},"agent_actions":{"view_html":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6","download_json":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6.json","view_paper":"https://pith.science/paper/NUSO4L65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05997&json=true","fetch_graph":"https://pith.science/api/pith-number/NUSO4L65BSL7USTP27LBZRLVS6/graph.json","fetch_events":"https://pith.science/api/pith-number/NUSO4L65BSL7USTP27LBZRLVS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6/action/storage_attestation","attest_author":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6/action/author_attestation","sign_citation":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6/action/citation_signature","submit_replication":"https://pith.science/pith/NUSO4L65BSL7USTP27LBZRLVS6/action/replication_record"}},"created_at":"2026-07-05T07:18:31.492273+00:00","updated_at":"2026-07-05T07:18:31.492273+00:00"}