{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LDADS4PWEHCJSNZN256I7MLHGB","short_pith_number":"pith:LDADS4PW","schema_version":"1.0","canonical_sha256":"58c03971f621c499372dd77c8fb1673068cf8498a285ed826f0e5c86cbdc8760","source":{"kind":"arxiv","id":"2602.11574","version":2},"attestation_state":"computed","paper":{"title":"Learning to Configure Agentic AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aditya Taparia, Ransalu Senanayake, Som Sagar","submitted_at":"2026-02-12T04:45:44Z","abstract_excerpt":"Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled today by fixed templates or hand-tuned heuristics that apply the same configuration regardless of query difficulty, leading to brittle behavior and wasted compute. To address this, we formulate agent configuration as a semi-Markov decision process (SMDP) where each configuration acts as a temporally extended option that determines how an agent system processes a query, and introduce introduce ARC (Agentic Resource & Configuration l"},"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":"2602.11574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T04:45:44Z","cross_cats_sorted":[],"title_canon_sha256":"5526843617073eabbbe120c0425c437cd4d454115c50de05a2a9100edeb138a5","abstract_canon_sha256":"276a54b290e856f8f5aa9f3918c8dffb4abc468750f8fc098ef8e4d455d687e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:23.111398Z","signature_b64":"Ad0zk05PyZXhuD4+xzC/W9V4TQK5Q+I8v5D5jtp2ptcGBLqTKKZJ0KUdg5uoj9xM+DoKe1SFJzovR8iW/HcqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c03971f621c499372dd77c8fb1673068cf8498a285ed826f0e5c86cbdc8760","last_reissued_at":"2026-05-21T01:04:23.110564Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:23.110564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Configure Agentic AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aditya Taparia, Ransalu Senanayake, Som Sagar","submitted_at":"2026-02-12T04:45:44Z","abstract_excerpt":"Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled today by fixed templates or hand-tuned heuristics that apply the same configuration regardless of query difficulty, leading to brittle behavior and wasted compute. To address this, we formulate agent configuration as a semi-Markov decision process (SMDP) where each configuration acts as a temporally extended option that determines how an agent system processes a query, and introduce introduce ARC (Agentic Resource & Configuration l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11574","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/2602.11574/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":"2602.11574","created_at":"2026-05-21T01:04:23.110670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11574v2","created_at":"2026-05-21T01:04:23.110670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11574","created_at":"2026-05-21T01:04:23.110670+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDADS4PWEHCJ","created_at":"2026-05-21T01:04:23.110670+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDADS4PWEHCJSNZN","created_at":"2026-05-21T01:04:23.110670+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDADS4PW","created_at":"2026-05-21T01:04:23.110670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB","json":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB.json","graph_json":"https://pith.science/api/pith-number/LDADS4PWEHCJSNZN256I7MLHGB/graph.json","events_json":"https://pith.science/api/pith-number/LDADS4PWEHCJSNZN256I7MLHGB/events.json","paper":"https://pith.science/paper/LDADS4PW"},"agent_actions":{"view_html":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB","download_json":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB.json","view_paper":"https://pith.science/paper/LDADS4PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11574&json=true","fetch_graph":"https://pith.science/api/pith-number/LDADS4PWEHCJSNZN256I7MLHGB/graph.json","fetch_events":"https://pith.science/api/pith-number/LDADS4PWEHCJSNZN256I7MLHGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB/action/storage_attestation","attest_author":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB/action/author_attestation","sign_citation":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB/action/citation_signature","submit_replication":"https://pith.science/pith/LDADS4PWEHCJSNZN256I7MLHGB/action/replication_record"}},"created_at":"2026-05-21T01:04:23.110670+00:00","updated_at":"2026-05-21T01:04:23.110670+00:00"}