{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N","short_pith_number":"pith:JFWDTT5N","schema_version":"1.0","canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","source":{"kind":"arxiv","id":"2604.09297","version":2},"attestation_state":"computed","paper":{"title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alina Geiger, Dominik Sobania, Federica Sarro, Jie M. Zhang, Jingzhi Gong, Lukas Twist, Ruizhen Gu, Shuo Han, Yazhuo Cao, Zhiwei Fei","submitted_at":"2026-04-10T13:08:01Z","abstract_excerpt":"Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE"},"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":"2604.09297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929","abstract_canon_sha256":"df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:10.908033Z","signature_b64":"aNRg51BKvPc17Z6GNnZZxQHjQVbAB4OngxWKEYs8e/Ah+76xPVozKu3Da7EsW3pO5BtTOdNoz0kqXuGI8XceBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","last_reissued_at":"2026-05-20T00:03:10.907210Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:10.907210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alina Geiger, Dominik Sobania, Federica Sarro, Jie M. Zhang, Jingzhi Gong, Lukas Twist, Ruizhen Gu, Shuo Han, Yazhuo Cao, Zhiwei Fei","submitted_at":"2026-04-10T13:08:01Z","abstract_excerpt":"Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cbcacd44beb112a8b4be55d46a21845dd6cf79d31e2ae3cfe8686f4c24a705b4"},"source":{"id":"2604.09297","kind":"arxiv","version":2},"verdict":{"id":"d8720abe-ad4d-44d5-9df5-d4da9c5e24a1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:21:55.619579Z","strongest_claim":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.","one_line_summary":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics.","pith_extraction_headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09297/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":"2604.09297","created_at":"2026-05-20T00:03:10.907334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09297v2","created_at":"2026-05-20T00:03:10.907334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09297","created_at":"2026-05-20T00:03:10.907334+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFWDTT5N2R3S","created_at":"2026-05-20T00:03:10.907334+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFWDTT5N2R3SLTIJ","created_at":"2026-05-20T00:03:10.907334+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFWDTT5N","created_at":"2026-05-20T00:03:10.907334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18401","citing_title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N","json":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N.json","graph_json":"https://pith.science/api/pith-number/JFWDTT5N2R3SLTIJFAQK3P2B5N/graph.json","events_json":"https://pith.science/api/pith-number/JFWDTT5N2R3SLTIJFAQK3P2B5N/events.json","paper":"https://pith.science/paper/JFWDTT5N"},"agent_actions":{"view_html":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N","download_json":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N.json","view_paper":"https://pith.science/paper/JFWDTT5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09297&json=true","fetch_graph":"https://pith.science/api/pith-number/JFWDTT5N2R3SLTIJFAQK3P2B5N/graph.json","fetch_events":"https://pith.science/api/pith-number/JFWDTT5N2R3SLTIJFAQK3P2B5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/action/storage_attestation","attest_author":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/action/author_attestation","sign_citation":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/action/citation_signature","submit_replication":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/action/replication_record"}},"created_at":"2026-05-20T00:03:10.907334+00:00","updated_at":"2026-05-20T00:03:10.907334+00:00"}