{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZOVUJGWDF5VNUX3ZSSIHCPPY5M","short_pith_number":"pith:ZOVUJGWD","schema_version":"1.0","canonical_sha256":"cbab449ac32f6ada5f799490713df8eb3cbe97ab4822e67b3a8dafa4c7ad8869","source":{"kind":"arxiv","id":"2305.14078","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"David Hsu, Wee Sun Lee, Zirui Zhao","submitted_at":"2023-05-23T13:56:31Z","abstract_excerpt":"Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in addition to a policy that acts on it. The world model and the policy can be combined in a search algorithm, such as Monte Carlo Tree Search (MCTS), to scale up task planning. In our new LLM-MCTS algorithm, the LLM-induced world model provides a commonsense prior belief for MCTS to achieve effective reasoning; the LLM-induced policy acts as a heuristic to guide the"},"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":"2305.14078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-05-23T13:56:31Z","cross_cats_sorted":[],"title_canon_sha256":"08dca81155b7b8999d11f73bc79c7eae30a605647db136346f218d8a6a5ba424","abstract_canon_sha256":"cbe350d011646f80ce35ac1cfbe8bfa834ebbe63af32d2bdad6f006e3d5237ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:27.476401Z","signature_b64":"06ZCPzBnqC5nSOd672yFPAOgr6HM+3gTXabEch8+6mTTr3DfNyboUBBX1Z3PPYR9XNZ23CyCnw9vayV4ULo6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbab449ac32f6ada5f799490713df8eb3cbe97ab4822e67b3a8dafa4c7ad8869","last_reissued_at":"2026-07-05T07:06:27.475943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:27.475943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"David Hsu, Wee Sun Lee, Zirui Zhao","submitted_at":"2023-05-23T13:56:31Z","abstract_excerpt":"Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in addition to a policy that acts on it. The world model and the policy can be combined in a search algorithm, such as Monte Carlo Tree Search (MCTS), to scale up task planning. In our new LLM-MCTS algorithm, the LLM-induced world model provides a commonsense prior belief for MCTS to achieve effective reasoning; the LLM-induced policy acts as a heuristic to guide the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14078","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/2305.14078/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":"2305.14078","created_at":"2026-07-05T07:06:27.475998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14078v2","created_at":"2026-07-05T07:06:27.475998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14078","created_at":"2026-07-05T07:06:27.475998+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOVUJGWDF5VN","created_at":"2026-07-05T07:06:27.475998+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOVUJGWDF5VNUX3Z","created_at":"2026-07-05T07:06:27.475998+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOVUJGWD","created_at":"2026-07-05T07:06:27.475998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2409.13107","citing_title":"Towards Robust Surgical Automation via Digital Twin Representations from Foundation Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2402.02716","citing_title":"Understanding the planning of LLM agents: A survey","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10827","citing_title":"Your Model Diversity, Not Method, Determines Reasoning Strategy","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01207","citing_title":"Efficient Causal Graph Discovery Using Large Language Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M","json":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M.json","graph_json":"https://pith.science/api/pith-number/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/graph.json","events_json":"https://pith.science/api/pith-number/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/events.json","paper":"https://pith.science/paper/ZOVUJGWD"},"agent_actions":{"view_html":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M","download_json":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M.json","view_paper":"https://pith.science/paper/ZOVUJGWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14078&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/action/storage_attestation","attest_author":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/action/author_attestation","sign_citation":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/action/citation_signature","submit_replication":"https://pith.science/pith/ZOVUJGWDF5VNUX3ZSSIHCPPY5M/action/replication_record"}},"created_at":"2026-07-05T07:06:27.475998+00:00","updated_at":"2026-07-05T07:06:27.475998+00:00"}