{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2AHLR3KUY3AFF36BJHGNOAODQO","short_pith_number":"pith:2AHLR3KU","schema_version":"1.0","canonical_sha256":"d00eb8ed54c6c052efc149ccd701c38380d10ecc3bc639d4cd04a43d84241bdb","source":{"kind":"arxiv","id":"2407.10031","version":2},"attestation_state":"computed","paper":{"title":"LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Adelmo Morrison Orozco, Aditya Kapoor, Anuj Mahajan, Brian Ichter, Darren Chen, Eric Robinson, Hamsa Balakrishnan, Jackson Zhang, James Harrison, Karthik Gopalakrishnan, Marina Ten Have, Siddharth Nayak, Vittal Thirumalai","submitted_at":"2024-07-14T00:12:44Z","abstract_excerpt":"The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), 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":"2407.10031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-14T00:12:44Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"69cfd35d1c11c8613a477a6e0f32ff4f91edf1352af93d0ecf42d1961b6c76a4","abstract_canon_sha256":"ef97a7a46fae8df0e9c512f0b2b7ba2ec45b147b490cf66adf3fd9d4589de055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:50.230413Z","signature_b64":"FESvzlV17wyFs4wyJG/Rwq/JJ4MuNOT2ffoNhP3hChYlMKeW7K9X6BJbAioA76RA+ls47voO6DPLrlxthrToCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d00eb8ed54c6c052efc149ccd701c38380d10ecc3bc639d4cd04a43d84241bdb","last_reissued_at":"2026-07-05T09:59:50.229953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:50.229953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Adelmo Morrison Orozco, Aditya Kapoor, Anuj Mahajan, Brian Ichter, Darren Chen, Eric Robinson, Hamsa Balakrishnan, Jackson Zhang, James Harrison, Karthik Gopalakrishnan, Marina Ten Have, Siddharth Nayak, Vittal Thirumalai","submitted_at":"2024-07-14T00:12:44Z","abstract_excerpt":"The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10031","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/2407.10031/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":"2407.10031","created_at":"2026-07-05T09:59:50.230011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10031v2","created_at":"2026-07-05T09:59:50.230011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10031","created_at":"2026-07-05T09:59:50.230011+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AHLR3KUY3AF","created_at":"2026-07-05T09:59:50.230011+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AHLR3KUY3AFF36B","created_at":"2026-07-05T09:59:50.230011+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AHLR3KU","created_at":"2026-07-05T09:59:50.230011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31422","citing_title":"Ask the World Before Acting: Environment Probing for Calibrated Agent World Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31073","citing_title":"MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10148","citing_title":"Closed-Loop Vision-Language Planning for Multi-Agent Coordination","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02334","citing_title":"Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11225","citing_title":"PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO","json":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO.json","graph_json":"https://pith.science/api/pith-number/2AHLR3KUY3AFF36BJHGNOAODQO/graph.json","events_json":"https://pith.science/api/pith-number/2AHLR3KUY3AFF36BJHGNOAODQO/events.json","paper":"https://pith.science/paper/2AHLR3KU"},"agent_actions":{"view_html":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO","download_json":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO.json","view_paper":"https://pith.science/paper/2AHLR3KU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10031&json=true","fetch_graph":"https://pith.science/api/pith-number/2AHLR3KUY3AFF36BJHGNOAODQO/graph.json","fetch_events":"https://pith.science/api/pith-number/2AHLR3KUY3AFF36BJHGNOAODQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO/action/storage_attestation","attest_author":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO/action/author_attestation","sign_citation":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO/action/citation_signature","submit_replication":"https://pith.science/pith/2AHLR3KUY3AFF36BJHGNOAODQO/action/replication_record"}},"created_at":"2026-07-05T09:59:50.230011+00:00","updated_at":"2026-07-05T09:59:50.230011+00:00"}