{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2CNCLREMXOTGBTLFWXMAZJKMO5","short_pith_number":"pith:2CNCLREM","schema_version":"1.0","canonical_sha256":"d09a25c48cbba660cd65b5d80ca54c7767f12070fe5ce8b936b905b2348a9637","source":{"kind":"arxiv","id":"2503.15520","version":1},"attestation_state":"computed","paper":{"title":"Agent-S: LLM Agentic workflow to automate Standard Operating Procedures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Mandar Kulkarni","submitted_at":"2025-02-03T09:04:48Z","abstract_excerpt":"AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer care operations, an SOP defines a logical step-by-step process for human agents to resolve customer issues. We observe that any step in the SOP can be categorized as user interaction or API call, while the logical flow in the SOP defines the navigation. We use LLMs augmented with memory and environments (API tools, user interface, external knowledge source) for"},"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":"2503.15520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-02-03T09:04:48Z","cross_cats_sorted":[],"title_canon_sha256":"5fdea737c9795c46537540c0b259e5f6efd789a6e0a1892efdf57713236111a9","abstract_canon_sha256":"d6db3d709b9b67d73d3884ab39fdd4cdb45f598f7f818cab553480008d9452ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:51.937435Z","signature_b64":"+3NisIF8zvHzM0RmnFuULqwrZ3S7cws9Tk+Miy3/c/6kXNOr4E2j5FVZ52CaKZKAWc+0mqJ/LgzJHx46wybMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09a25c48cbba660cd65b5d80ca54c7767f12070fe5ce8b936b905b2348a9637","last_reissued_at":"2026-07-05T10:35:51.937007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:51.937007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-S: LLM Agentic workflow to automate Standard Operating Procedures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Mandar Kulkarni","submitted_at":"2025-02-03T09:04:48Z","abstract_excerpt":"AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer care operations, an SOP defines a logical step-by-step process for human agents to resolve customer issues. We observe that any step in the SOP can be categorized as user interaction or API call, while the logical flow in the SOP defines the navigation. We use LLMs augmented with memory and environments (API tools, user interface, external knowledge source) for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15520","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/2503.15520/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":"2503.15520","created_at":"2026-07-05T10:35:51.937066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15520v1","created_at":"2026-07-05T10:35:51.937066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15520","created_at":"2026-07-05T10:35:51.937066+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CNCLREMXOTG","created_at":"2026-07-05T10:35:51.937066+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CNCLREMXOTGBTLF","created_at":"2026-07-05T10:35:51.937066+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CNCLREM","created_at":"2026-07-05T10:35:51.937066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07339","citing_title":"Tools as Continuous Flow for Evolving Agentic Reasoning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5","json":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5.json","graph_json":"https://pith.science/api/pith-number/2CNCLREMXOTGBTLFWXMAZJKMO5/graph.json","events_json":"https://pith.science/api/pith-number/2CNCLREMXOTGBTLFWXMAZJKMO5/events.json","paper":"https://pith.science/paper/2CNCLREM"},"agent_actions":{"view_html":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5","download_json":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5.json","view_paper":"https://pith.science/paper/2CNCLREM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15520&json=true","fetch_graph":"https://pith.science/api/pith-number/2CNCLREMXOTGBTLFWXMAZJKMO5/graph.json","fetch_events":"https://pith.science/api/pith-number/2CNCLREMXOTGBTLFWXMAZJKMO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5/action/storage_attestation","attest_author":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5/action/author_attestation","sign_citation":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5/action/citation_signature","submit_replication":"https://pith.science/pith/2CNCLREMXOTGBTLFWXMAZJKMO5/action/replication_record"}},"created_at":"2026-07-05T10:35:51.937066+00:00","updated_at":"2026-07-05T10:35:51.937066+00:00"}