{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZY53KM2RBDOUVBP6TFCQZJOVFG","short_pith_number":"pith:ZY53KM2R","schema_version":"1.0","canonical_sha256":"ce3bb5335108dd4a85fe99450ca5d529a1d962022cd6762cac8630129a6bc0ec","source":{"kind":"arxiv","id":"2508.19076","version":1},"attestation_state":"computed","paper":{"title":"HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gaihong Yu, Xiaoqiu Le, Yuan Chang, Ziyue Li","submitted_at":"2025-08-26T14:37:48Z","abstract_excerpt":"Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance, causing disorientation and failures in complex tasks, as well as insufficient continuous oversight during execution, rendering them unresponsive to environmental changes and prone to deviations. To tackle these challenges, we introduce HiPlan, a hierarchical planning framework that provides adaptive global-local guidance to boost LLM-based agents'decision-making."},"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":"2508.19076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T14:37:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7247b649112a13210fefa33019956ec77d0a592a1f7dcbc8773475c61a5a642","abstract_canon_sha256":"c5eebcc86a42dab8054add6de79bee61d699f75f2ac76d317137364b78853c7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:36.370461Z","signature_b64":"ATwYxfEEOwZS93rMkOR3NiRiWkGpQumvfFMYB9jxieezDDMZhPOKIpVOsz+Pjh4Io+njfRDhWY+PEQE5pITRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce3bb5335108dd4a85fe99450ca5d529a1d962022cd6762cac8630129a6bc0ec","last_reissued_at":"2026-07-05T11:59:36.369975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:36.369975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gaihong Yu, Xiaoqiu Le, Yuan Chang, Ziyue Li","submitted_at":"2025-08-26T14:37:48Z","abstract_excerpt":"Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance, causing disorientation and failures in complex tasks, as well as insufficient continuous oversight during execution, rendering them unresponsive to environmental changes and prone to deviations. To tackle these challenges, we introduce HiPlan, a hierarchical planning framework that provides adaptive global-local guidance to boost LLM-based agents'decision-making."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19076","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/2508.19076/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":"2508.19076","created_at":"2026-07-05T11:59:36.370036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19076v1","created_at":"2026-07-05T11:59:36.370036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19076","created_at":"2026-07-05T11:59:36.370036+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZY53KM2RBDOU","created_at":"2026-07-05T11:59:36.370036+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZY53KM2RBDOUVBP6","created_at":"2026-07-05T11:59:36.370036+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZY53KM2R","created_at":"2026-07-05T11:59:36.370036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.00977","citing_title":"HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG","json":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG.json","graph_json":"https://pith.science/api/pith-number/ZY53KM2RBDOUVBP6TFCQZJOVFG/graph.json","events_json":"https://pith.science/api/pith-number/ZY53KM2RBDOUVBP6TFCQZJOVFG/events.json","paper":"https://pith.science/paper/ZY53KM2R"},"agent_actions":{"view_html":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG","download_json":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG.json","view_paper":"https://pith.science/paper/ZY53KM2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19076&json=true","fetch_graph":"https://pith.science/api/pith-number/ZY53KM2RBDOUVBP6TFCQZJOVFG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZY53KM2RBDOUVBP6TFCQZJOVFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG/action/storage_attestation","attest_author":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG/action/author_attestation","sign_citation":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG/action/citation_signature","submit_replication":"https://pith.science/pith/ZY53KM2RBDOUVBP6TFCQZJOVFG/action/replication_record"}},"created_at":"2026-07-05T11:59:36.370036+00:00","updated_at":"2026-07-05T11:59:36.370036+00:00"}