{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CKXMOHIZEO36C6QU63IO6B5KDP","short_pith_number":"pith:CKXMOHIZ","schema_version":"1.0","canonical_sha256":"12aec71d1923b7e17a14f6d0ef07aa1bfc13d406ad7c4041e72839d4e67cfca9","source":{"kind":"arxiv","id":"2507.14447","version":2},"attestation_state":"computed","paper":{"title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Gang Li, Guancheng Zeng, Haowen Hu, Jiawang Hu, Jingjing Mo, Linyan Huang, Pengxu Qiu, Qiuyang Feng, Shaohua Qi, Shuang Li, Wenqiang Han, Xueyi Chen, Yaxuan Mao, Yifan Nie, Yujia Wang, Zhantao Wang","submitted_at":"2025-07-19T02:46:19Z","abstract_excerpt":"The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly "},"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":"2507.14447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-19T02:46:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ba22777c7bb540f1671cab1966ca835683e011d38e69311fdca643a3da7244fb","abstract_canon_sha256":"474c12af8cdeafc58774f3ae08b3f7cae00fe85b485754d337c0bf42015e5527"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:57.674214Z","signature_b64":"agpFJOfdFh/2Mhe23ygr+Ny0/F2HHtP1g4kNOQEh818Z6LA+UcKxyFB730xt8B2/WpXJQzgjbgJkLkqmxCasBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12aec71d1923b7e17a14f6d0ef07aa1bfc13d406ad7c4041e72839d4e67cfca9","last_reissued_at":"2026-07-05T11:40:57.673608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:57.673608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Gang Li, Guancheng Zeng, Haowen Hu, Jiawang Hu, Jingjing Mo, Linyan Huang, Pengxu Qiu, Qiuyang Feng, Shaohua Qi, Shuang Li, Wenqiang Han, Xueyi Chen, Yaxuan Mao, Yifan Nie, Yujia Wang, Zhantao Wang","submitted_at":"2025-07-19T02:46:19Z","abstract_excerpt":"The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14447","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/2507.14447/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":"2507.14447","created_at":"2026-07-05T11:40:57.673724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14447v2","created_at":"2026-07-05T11:40:57.673724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14447","created_at":"2026-07-05T11:40:57.673724+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKXMOHIZEO36","created_at":"2026-07-05T11:40:57.673724+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKXMOHIZEO36C6QU","created_at":"2026-07-05T11:40:57.673724+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKXMOHIZ","created_at":"2026-07-05T11:40:57.673724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26302","citing_title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11378","citing_title":"From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07339","citing_title":"Tools as Continuous Flow for Evolving Agentic Reasoning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP","json":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP.json","graph_json":"https://pith.science/api/pith-number/CKXMOHIZEO36C6QU63IO6B5KDP/graph.json","events_json":"https://pith.science/api/pith-number/CKXMOHIZEO36C6QU63IO6B5KDP/events.json","paper":"https://pith.science/paper/CKXMOHIZ"},"agent_actions":{"view_html":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP","download_json":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP.json","view_paper":"https://pith.science/paper/CKXMOHIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14447&json=true","fetch_graph":"https://pith.science/api/pith-number/CKXMOHIZEO36C6QU63IO6B5KDP/graph.json","fetch_events":"https://pith.science/api/pith-number/CKXMOHIZEO36C6QU63IO6B5KDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP/action/storage_attestation","attest_author":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP/action/author_attestation","sign_citation":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP/action/citation_signature","submit_replication":"https://pith.science/pith/CKXMOHIZEO36C6QU63IO6B5KDP/action/replication_record"}},"created_at":"2026-07-05T11:40:57.673724+00:00","updated_at":"2026-07-05T11:40:57.673724+00:00"}