{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7MFJVP3RIPN53FNCSQVYC3ZDA","short_pith_number":"pith:O7MFJVP3","schema_version":"1.0","canonical_sha256":"77d854d5fb8a1edeecad14a15c0b791829b3dfc00d5e899cb2ced3978b77324f","source":{"kind":"arxiv","id":"2412.17149","version":1},"attestation_state":"computed","paper":{"title":"A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.MA","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hassan Sawaf, Kamer Ali Yuksel","submitted_at":"2024-12-22T20:08:04Z","abstract_excerpt":"Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and interactions. This paper introduces a framework for autonomously optimizing Agentic AI solutions across industries, such as NLP-driven enterprise applications. The system employs agents for Refinement, Execution, Evaluation, Modification, and Documentation, leveraging iterative feedback loops powered by an LLM (Llama 3.2-3B). The framework achieves optimal performa"},"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":"2412.17149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T20:08:04Z","cross_cats_sorted":["cs.AI","cs.ET","cs.MA","cs.NE"],"title_canon_sha256":"d3e1140a0a29f06da91f873e03007d43f6afc90cd85ced984fb5cae9e4e2fde5","abstract_canon_sha256":"417eb249b0003681acbf692ce12a7bf4cd9bcb5c14c0a6a6258deca91fa341cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:18.247804Z","signature_b64":"prAaQ226wI+YyimnK53kihYcMtOOQ/gVq5uAEGeKkbWlysAux6JcVX+gIky4BoCfCk76yo1aWjarNemmWAbuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d854d5fb8a1edeecad14a15c0b791829b3dfc00d5e899cb2ced3978b77324f","last_reissued_at":"2026-07-05T09:53:18.247363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:18.247363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.MA","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hassan Sawaf, Kamer Ali Yuksel","submitted_at":"2024-12-22T20:08:04Z","abstract_excerpt":"Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and interactions. This paper introduces a framework for autonomously optimizing Agentic AI solutions across industries, such as NLP-driven enterprise applications. The system employs agents for Refinement, Execution, Evaluation, Modification, and Documentation, leveraging iterative feedback loops powered by an LLM (Llama 3.2-3B). The framework achieves optimal performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17149","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/2412.17149/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":"2412.17149","created_at":"2026-07-05T09:53:18.247415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17149v1","created_at":"2026-07-05T09:53:18.247415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17149","created_at":"2026-07-05T09:53:18.247415+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7MFJVP3RIPN","created_at":"2026-07-05T09:53:18.247415+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7MFJVP3RIPN53FN","created_at":"2026-07-05T09:53:18.247415+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7MFJVP3","created_at":"2026-07-05T09:53:18.247415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA","json":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA.json","graph_json":"https://pith.science/api/pith-number/O7MFJVP3RIPN53FNCSQVYC3ZDA/graph.json","events_json":"https://pith.science/api/pith-number/O7MFJVP3RIPN53FNCSQVYC3ZDA/events.json","paper":"https://pith.science/paper/O7MFJVP3"},"agent_actions":{"view_html":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA","download_json":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA.json","view_paper":"https://pith.science/paper/O7MFJVP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17149&json=true","fetch_graph":"https://pith.science/api/pith-number/O7MFJVP3RIPN53FNCSQVYC3ZDA/graph.json","fetch_events":"https://pith.science/api/pith-number/O7MFJVP3RIPN53FNCSQVYC3ZDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA/action/storage_attestation","attest_author":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA/action/author_attestation","sign_citation":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA/action/citation_signature","submit_replication":"https://pith.science/pith/O7MFJVP3RIPN53FNCSQVYC3ZDA/action/replication_record"}},"created_at":"2026-07-05T09:53:18.247415+00:00","updated_at":"2026-07-05T09:53:18.247415+00:00"}