{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BIGRANI45ZW23VX5NRC5RP72MN","short_pith_number":"pith:BIGRANI4","schema_version":"1.0","canonical_sha256":"0a0d10351cee6dadd6fd6c45d8bffa635c76530d415f63a0eb42243c74024a1a","source":{"kind":"arxiv","id":"2509.08646","version":1},"attestation_state":"computed","paper":{"title":"Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.CR","authors_text":"Christian Schroeder de Witt, Klaudia Krawiecka, Ron F. Del Rosario","submitted_at":"2025-09-10T14:41:07Z","abstract_excerpt":"As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is paramount. This paper provides a comprehensive guide to the ``Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages in predictability, cost-efficiency, and reasoning quality over reactive patterns like ReAct (Reason + "},"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":"2509.08646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-09-10T14:41:07Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"82768cc38e09b9830c8035260e5a321e014fa8d9ca9029fa7f17d131db49ed05","abstract_canon_sha256":"7f7a5288ab9abc09f0800da1d65263b1e99ee07c61bfaf804084c441153de980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:33.722088Z","signature_b64":"+LZpTF5bJpnEhvDS48gRa2TYAZAXtfeMAarb6NlLA50G334Lj6/6vsWeez7ACdCnq8YVhHyNy1dagybPXpfAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a0d10351cee6dadd6fd6c45d8bffa635c76530d415f63a0eb42243c74024a1a","last_reissued_at":"2026-07-05T12:08:33.721618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:33.721618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.CR","authors_text":"Christian Schroeder de Witt, Klaudia Krawiecka, Ron F. Del Rosario","submitted_at":"2025-09-10T14:41:07Z","abstract_excerpt":"As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is paramount. This paper provides a comprehensive guide to the ``Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages in predictability, cost-efficiency, and reasoning quality over reactive patterns like ReAct (Reason + "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08646","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/2509.08646/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":"2509.08646","created_at":"2026-07-05T12:08:33.721677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08646v1","created_at":"2026-07-05T12:08:33.721677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08646","created_at":"2026-07-05T12:08:33.721677+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIGRANI45ZW2","created_at":"2026-07-05T12:08:33.721677+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIGRANI45ZW23VX5","created_at":"2026-07-05T12:08:33.721677+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIGRANI4","created_at":"2026-07-05T12:08:33.721677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14628","citing_title":"SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13346","citing_title":"AgentSPEX: An Agent SPecification and EXecution Language","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12986","citing_title":"Parallax: Why AI Agents That Think Must Never Act","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN","json":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN.json","graph_json":"https://pith.science/api/pith-number/BIGRANI45ZW23VX5NRC5RP72MN/graph.json","events_json":"https://pith.science/api/pith-number/BIGRANI45ZW23VX5NRC5RP72MN/events.json","paper":"https://pith.science/paper/BIGRANI4"},"agent_actions":{"view_html":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN","download_json":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN.json","view_paper":"https://pith.science/paper/BIGRANI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08646&json=true","fetch_graph":"https://pith.science/api/pith-number/BIGRANI45ZW23VX5NRC5RP72MN/graph.json","fetch_events":"https://pith.science/api/pith-number/BIGRANI45ZW23VX5NRC5RP72MN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN/action/storage_attestation","attest_author":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN/action/author_attestation","sign_citation":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN/action/citation_signature","submit_replication":"https://pith.science/pith/BIGRANI45ZW23VX5NRC5RP72MN/action/replication_record"}},"created_at":"2026-07-05T12:08:33.721677+00:00","updated_at":"2026-07-05T12:08:33.721677+00:00"}