{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VILIFK4KUVMPEVQD2OVMQO3OXF","short_pith_number":"pith:VILIFK4K","schema_version":"1.0","canonical_sha256":"aa1682ab8aa558f25603d3aac83b6eb943c7c63a452de942008bcbc951efc19c","source":{"kind":"arxiv","id":"2307.02485","version":2},"attestation_state":"computed","paper":{"title":"Building Cooperative Embodied Agents Modularly with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Hongxin Zhang, Jiaming Shan, Joshua B. Tenenbaum, Qinhong Zhou, Tianmin Shu, Weihua Du, Yilun Du","submitted_at":"2023-07-05T17:59:27Z","abstract_excerpt":"In this work, we address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. While previous research either presupposes a cost-free communication channel or relies on a centralized controller with shared observations, we harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework that integrates with perception, memory, and ex"},"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":"2307.02485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-05T17:59:27Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"1b5b35a11ad35b67f01183db4f991ce8766ce343668e5fbd74dfa64033f65f87","abstract_canon_sha256":"380674306a39a5e505f96ee18cafd93516d85e4a8590fea8a047d582b8918fb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:18.094304Z","signature_b64":"KtKmFaiK78L4hGzL+ruQD9egwMztGEqIC4hey/moaWBZSXdZSfgXaIkUOkh2/RpJqX9Ls9/ZcGp1CKofr5PGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1682ab8aa558f25603d3aac83b6eb943c7c63a452de942008bcbc951efc19c","last_reissued_at":"2026-07-05T10:30:18.093820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:18.093820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Cooperative Embodied Agents Modularly with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Hongxin Zhang, Jiaming Shan, Joshua B. Tenenbaum, Qinhong Zhou, Tianmin Shu, Weihua Du, Yilun Du","submitted_at":"2023-07-05T17:59:27Z","abstract_excerpt":"In this work, we address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. While previous research either presupposes a cost-free communication channel or relies on a centralized controller with shared observations, we harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework that integrates with perception, memory, and ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02485","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/2307.02485/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":"2307.02485","created_at":"2026-07-05T10:30:18.093872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02485v2","created_at":"2026-07-05T10:30:18.093872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02485","created_at":"2026-07-05T10:30:18.093872+00:00"},{"alias_kind":"pith_short_12","alias_value":"VILIFK4KUVMP","created_at":"2026-07-05T10:30:18.093872+00:00"},{"alias_kind":"pith_short_16","alias_value":"VILIFK4KUVMPEVQD","created_at":"2026-07-05T10:30:18.093872+00:00"},{"alias_kind":"pith_short_8","alias_value":"VILIFK4K","created_at":"2026-07-05T10:30:18.093872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19904","citing_title":"Toward Temporal Realism in City-Scale Crisis Response Simulation using LLM Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":217,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11109","citing_title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13958","citing_title":"ToolRL: Reward is All Tool Learning Needs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01680","citing_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18975","citing_title":"Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05484","citing_title":"CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04664","citing_title":"ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13558","citing_title":"AgentComm: Semantic Communication for Embodied Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15607","citing_title":"Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF","json":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF.json","graph_json":"https://pith.science/api/pith-number/VILIFK4KUVMPEVQD2OVMQO3OXF/graph.json","events_json":"https://pith.science/api/pith-number/VILIFK4KUVMPEVQD2OVMQO3OXF/events.json","paper":"https://pith.science/paper/VILIFK4K"},"agent_actions":{"view_html":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF","download_json":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF.json","view_paper":"https://pith.science/paper/VILIFK4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02485&json=true","fetch_graph":"https://pith.science/api/pith-number/VILIFK4KUVMPEVQD2OVMQO3OXF/graph.json","fetch_events":"https://pith.science/api/pith-number/VILIFK4KUVMPEVQD2OVMQO3OXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF/action/storage_attestation","attest_author":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF/action/author_attestation","sign_citation":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF/action/citation_signature","submit_replication":"https://pith.science/pith/VILIFK4KUVMPEVQD2OVMQO3OXF/action/replication_record"}},"created_at":"2026-07-05T10:30:18.093872+00:00","updated_at":"2026-07-05T10:30:18.093872+00:00"}