{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQC3MIZK4JXYW4D4T65C7WO4MS","short_pith_number":"pith:FQC3MIZK","schema_version":"1.0","canonical_sha256":"2c05b6232ae26f8b707c9fba2fd9dc6496c90d77599426e231b5244403887efe","source":{"kind":"arxiv","id":"2505.05108","version":2},"attestation_state":"computed","paper":{"title":"Multi-agent Embodied AI: Advances and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Bingzhao Gao, Gang Wang, Jian Sun, Lei Yuan, Meiqin Liu, Ning Ding, Ruiqi Xue, Xinhu Zheng, Yang Yu, Zhaohan Feng","submitted_at":"2025-05-08T10:13:53Z","abstract_excerpt":"Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments. Through the use of sensors for input and actuators for action, these systems can learn and adapt based on real-world feedback, allowing them to perform tasks effectively in dynamic and unpredictable environments. As techniques such as deep learning (DL), reinforcement learning (RL), and large language models (LLMs) mature, embodied A"},"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":"2505.05108","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-08T10:13:53Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d209b2b9980c1bf88761b57092d0c060f80f27eed4f915e43df5b5378db38f39","abstract_canon_sha256":"023ff7083cc3be2ff6b24d77dc95d5f94dc383f84c2472cc4427b772173cdc6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:10.315339Z","signature_b64":"WfuuB8SLcFIwd4t6r9Zda1+iELhEOGyXzC3K55hs9EH+RmZEA+pRJNearXGw5QfZcx0dDctmBqc+n3DVP9Y8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c05b6232ae26f8b707c9fba2fd9dc6496c90d77599426e231b5244403887efe","last_reissued_at":"2026-07-05T11:25:10.314859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:10.314859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-agent Embodied AI: Advances and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Bingzhao Gao, Gang Wang, Jian Sun, Lei Yuan, Meiqin Liu, Ning Ding, Ruiqi Xue, Xinhu Zheng, Yang Yu, Zhaohan Feng","submitted_at":"2025-05-08T10:13:53Z","abstract_excerpt":"Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments. Through the use of sensors for input and actuators for action, these systems can learn and adapt based on real-world feedback, allowing them to perform tasks effectively in dynamic and unpredictable environments. As techniques such as deep learning (DL), reinforcement learning (RL), and large language models (LLMs) mature, embodied A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05108","kind":"arxiv","version":2},"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/2505.05108/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":"2505.05108","created_at":"2026-07-05T11:25:10.314913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05108v2","created_at":"2026-07-05T11:25:10.314913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05108","created_at":"2026-07-05T11:25:10.314913+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQC3MIZK4JXY","created_at":"2026-07-05T11:25:10.314913+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQC3MIZK4JXYW4D4","created_at":"2026-07-05T11:25:10.314913+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQC3MIZK","created_at":"2026-07-05T11:25:10.314913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25389","citing_title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04349","citing_title":"MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20583","citing_title":"Physical-AI: From Channel Awareness to Environmental Intelligence in 6G Wireless Networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22446","citing_title":"Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11607","citing_title":"Low-Altitude Wireless Networks: A Comprehensive Survey","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10586","citing_title":"Safe Planning in Interactive Environments via Iterative Policy Updates and Adversarially Robust Conformal Prediction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01194","citing_title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05484","citing_title":"CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13558","citing_title":"AgentComm: Semantic Communication for Embodied Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13800","citing_title":"EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18564","citing_title":"MultiWorld: Scalable Multi-Agent Multi-View Video World Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05017","citing_title":"Position: Embodied AI Requires a Privacy-Utility Trade-off","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS","json":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS.json","graph_json":"https://pith.science/api/pith-number/FQC3MIZK4JXYW4D4T65C7WO4MS/graph.json","events_json":"https://pith.science/api/pith-number/FQC3MIZK4JXYW4D4T65C7WO4MS/events.json","paper":"https://pith.science/paper/FQC3MIZK"},"agent_actions":{"view_html":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS","download_json":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS.json","view_paper":"https://pith.science/paper/FQC3MIZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05108&json=true","fetch_graph":"https://pith.science/api/pith-number/FQC3MIZK4JXYW4D4T65C7WO4MS/graph.json","fetch_events":"https://pith.science/api/pith-number/FQC3MIZK4JXYW4D4T65C7WO4MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS/action/storage_attestation","attest_author":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS/action/author_attestation","sign_citation":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS/action/citation_signature","submit_replication":"https://pith.science/pith/FQC3MIZK4JXYW4D4T65C7WO4MS/action/replication_record"}},"created_at":"2026-07-05T11:25:10.314913+00:00","updated_at":"2026-07-05T11:25:10.314913+00:00"}