{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7MA54DW3MCWHBVJP3YGA2WMX25","short_pith_number":"pith:7MA54DW3","schema_version":"1.0","canonical_sha256":"fb01de0edb60ac70d52fde0c0d5997d746867bbadbe916d5fab7cc68302ae749","source":{"kind":"arxiv","id":"2608.04588","version":1},"attestation_state":"computed","paper":{"title":"EASy: Towards Efficient LLM-Based Agentic System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Junnan Liu, Linhao Luo, Thuy-Trang Vu","submitted_at":"2026-08-05T08:50:36Z","abstract_excerpt":"Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimi"},"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":"2608.04588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T08:50:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7de4b9f5711e549cc7289c0ec663c073d26ab25e532fd1fbd1193afe2ac84fff","abstract_canon_sha256":"7e16722fefbee8729670902e1e9bc5b8b85ca676e12f109226730438063f12eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:36:13.095525Z","signature_b64":"zH+oulxXiKmv1yEC7DFG6pSJ59QyVU5CgW8BD2BFjTjG2J1lCki7BXfWPUijWSlu5dTwG411+GP2hKumIhjECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb01de0edb60ac70d52fde0c0d5997d746867bbadbe916d5fab7cc68302ae749","last_reissued_at":"2026-08-06T01:36:13.094164Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:36:13.094164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EASy: Towards Efficient LLM-Based Agentic System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Junnan Liu, Linhao Luo, Thuy-Trang Vu","submitted_at":"2026-08-05T08:50:36Z","abstract_excerpt":"Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04588","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/2608.04588/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":"2608.04588","created_at":"2026-08-06T01:36:13.095927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04588v1","created_at":"2026-08-06T01:36:13.095927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04588","created_at":"2026-08-06T01:36:13.095927+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MA54DW3MCWH","created_at":"2026-08-06T01:36:13.095927+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MA54DW3MCWHBVJP","created_at":"2026-08-06T01:36:13.095927+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MA54DW3","created_at":"2026-08-06T01:36:13.095927+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/7MA54DW3MCWHBVJP3YGA2WMX25","json":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25.json","graph_json":"https://pith.science/api/pith-number/7MA54DW3MCWHBVJP3YGA2WMX25/graph.json","events_json":"https://pith.science/api/pith-number/7MA54DW3MCWHBVJP3YGA2WMX25/events.json","paper":"https://pith.science/paper/7MA54DW3"},"agent_actions":{"view_html":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25","download_json":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25.json","view_paper":"https://pith.science/paper/7MA54DW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04588&json=true","fetch_graph":"https://pith.science/api/pith-number/7MA54DW3MCWHBVJP3YGA2WMX25/graph.json","fetch_events":"https://pith.science/api/pith-number/7MA54DW3MCWHBVJP3YGA2WMX25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25/action/storage_attestation","attest_author":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25/action/author_attestation","sign_citation":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25/action/citation_signature","submit_replication":"https://pith.science/pith/7MA54DW3MCWHBVJP3YGA2WMX25/action/replication_record"}},"created_at":"2026-08-06T01:36:13.095927+00:00","updated_at":"2026-08-06T01:36:13.095927+00:00"}