{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H6KWZFSQQNZWIEOI2FR6HCVEZQ","short_pith_number":"pith:H6KWZFSQ","schema_version":"1.0","canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","source":{"kind":"arxiv","id":"2605.14504","version":1},"attestation_state":"computed","paper":{"title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Pang, Jing Liu, Longteng Guo, Ruyi Ji, Xingjian He, Yanghong Mei, Zilin Zhu, Zongxun Zhang","submitted_at":"2026-05-14T07:47:53Z","abstract_excerpt":"Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed task categories. We introduce LongAct, a benchmark designed to evaluate planning-level autonomy in long-horizon household tasks specified through free-form instructions. By abstracting away embodiment-specific low-level control, LongAct isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"252a621d8f7b57ae821328d3607fa3fa1e1d377ae7f8fc272c71550255cd8e83","abstract_canon_sha256":"db8c4a3e1eb299b0b1ab53c841f726d0d7d7952d4921139f945592bfb70327db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.277782Z","signature_b64":"eUqK6tA7zv7EPiBPWZrlKOHpeswBnwmOO4wOtR1jBUOQDgpF5+qVfBvc1+f3+Sq7dp7FT8Xqt2+AbsJStmDCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","last_reissued_at":"2026-05-17T23:39:06.276874Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.276874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Pang, Jing Liu, Longteng Guo, Ruyi Ji, Xingjian He, Yanghong Mei, Zilin Zhu, Zongxun Zhang","submitted_at":"2026-05-14T07:47:53Z","abstract_excerpt":"Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed task categories. We introduce LongAct, a benchmark designed to evaluate planning-level autonomy in long-horizon household tasks specified through free-form instructions. By abstracting away embodiment-specific low-level control, LongAct isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ec12b714591e2539c6a20c56a8798200702d62b6d8ea32579e2375c6d12dd29d"},"source":{"id":"2605.14504","kind":"arxiv","version":1},"verdict":{"id":"94bc80ce-e9cf-49aa-b028-9585781dec0f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:55:07.807981Z","strongest_claim":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success.","one_line_summary":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism.","pith_extraction_headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size."},"references":{"count":43,"sample":[{"doi":"","year":2025,"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","ref_index":1,"cited_arxiv_id":"2505.09388","is_internal_anchor":true},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":2,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"H. Liu, C. Li, Q. Wu, and Y . J. Lee. Visual instruction tuning.Advances in Neural Information Processing Systems, 36:1–19, 2023","work_id":"4eec8a8e-8c6e-46ee-8008-9b1dd58415a1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":4,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2023,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","ref_index":5,"cited_arxiv_id":"2312.11805","is_internal_anchor":true}],"resolved_work":43,"snapshot_sha256":"21571ef359ea4e79e652bc800ce523debebc34db345e2391734a67fe6616f61d","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d547d575035ac5376155c4db5e45601102cffa2ea632f260cf140bd9dc162946"},"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":"2605.14504","created_at":"2026-05-17T23:39:06.277002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14504v1","created_at":"2026-05-17T23:39:06.277002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14504","created_at":"2026-05-17T23:39:06.277002+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6KWZFSQQNZW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6KWZFSQQNZWIEOI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6KWZFSQ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ","json":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ.json","graph_json":"https://pith.science/api/pith-number/H6KWZFSQQNZWIEOI2FR6HCVEZQ/graph.json","events_json":"https://pith.science/api/pith-number/H6KWZFSQQNZWIEOI2FR6HCVEZQ/events.json","paper":"https://pith.science/paper/H6KWZFSQ"},"agent_actions":{"view_html":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ","download_json":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ.json","view_paper":"https://pith.science/paper/H6KWZFSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14504&json=true","fetch_graph":"https://pith.science/api/pith-number/H6KWZFSQQNZWIEOI2FR6HCVEZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/H6KWZFSQQNZWIEOI2FR6HCVEZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/action/storage_attestation","attest_author":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/action/author_attestation","sign_citation":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/action/citation_signature","submit_replication":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/action/replication_record"}},"created_at":"2026-05-17T23:39:06.277002+00:00","updated_at":"2026-05-17T23:39:06.277002+00:00"}