{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5BP6GWJTUBY3JJTBYSLZ7WIFBL","short_pith_number":"pith:5BP6GWJT","schema_version":"1.0","canonical_sha256":"e85fe35933a071b4a661c4979fd9050ae0348a1a9d5e08e242fd242f9d890789","source":{"kind":"arxiv","id":"2506.02683","version":1},"attestation_state":"computed","paper":{"title":"Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cen Chen, Hao Peng, Huiping Zhuang, Weikai Lu, Yiling Tao, Yun Dai, Zhengdong Lu, Ziqian Zeng, Zixuan Chen","submitted_at":"2025-06-03T09:33:13Z","abstract_excerpt":"Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heavy constraints and cascading errors. To address these limitations, we propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM). Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan. In addition, our approach incorporates 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":"2506.02683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"2a3332be8d6ad3dd5e81d5497994340f6ac22f201c19fdad4b0de474b2005a44","abstract_canon_sha256":"7b85b2e9aa5cf062c4372fe4a76ee630cf705bbde4f196d662b9f90b06e8f191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:06.424195Z","signature_b64":"vl+znTZ/VErdFU70IwvrdNPWN3C/4KgMJbo5ibzEklS5lax5Kc2g/71aRW3dOqsweD5b4MCao9WrBPXtSMkXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e85fe35933a071b4a661c4979fd9050ae0348a1a9d5e08e242fd242f9d890789","last_reissued_at":"2026-07-05T11:15:06.423709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:06.423709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cen Chen, Hao Peng, Huiping Zhuang, Weikai Lu, Yiling Tao, Yun Dai, Zhengdong Lu, Ziqian Zeng, Zixuan Chen","submitted_at":"2025-06-03T09:33:13Z","abstract_excerpt":"Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heavy constraints and cascading errors. To address these limitations, we propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM). Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan. In addition, our approach incorporates a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02683","kind":"arxiv","version":1},"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/2506.02683/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":"2506.02683","created_at":"2026-07-05T11:15:06.423764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02683v1","created_at":"2026-07-05T11:15:06.423764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02683","created_at":"2026-07-05T11:15:06.423764+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BP6GWJTUBY3","created_at":"2026-07-05T11:15:06.423764+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BP6GWJTUBY3JJTB","created_at":"2026-07-05T11:15:06.423764+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BP6GWJT","created_at":"2026-07-05T11:15:06.423764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03308","citing_title":"Revisiting the Travel Planning Capabilities of Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21354","citing_title":"Decoupled Travel Planning with Behavior Forest","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL","json":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL.json","graph_json":"https://pith.science/api/pith-number/5BP6GWJTUBY3JJTBYSLZ7WIFBL/graph.json","events_json":"https://pith.science/api/pith-number/5BP6GWJTUBY3JJTBYSLZ7WIFBL/events.json","paper":"https://pith.science/paper/5BP6GWJT"},"agent_actions":{"view_html":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL","download_json":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL.json","view_paper":"https://pith.science/paper/5BP6GWJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02683&json=true","fetch_graph":"https://pith.science/api/pith-number/5BP6GWJTUBY3JJTBYSLZ7WIFBL/graph.json","fetch_events":"https://pith.science/api/pith-number/5BP6GWJTUBY3JJTBYSLZ7WIFBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL/action/storage_attestation","attest_author":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL/action/author_attestation","sign_citation":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL/action/citation_signature","submit_replication":"https://pith.science/pith/5BP6GWJTUBY3JJTBYSLZ7WIFBL/action/replication_record"}},"created_at":"2026-07-05T11:15:06.423764+00:00","updated_at":"2026-07-05T11:15:06.423764+00:00"}