{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K44Q3IYRIZ2JMRNA65FWHZZSBA","short_pith_number":"pith:K44Q3IYR","schema_version":"1.0","canonical_sha256":"57390da31146749645a0f74b63e732081dddeb6ac76348db5c821d9229bf2a27","source":{"kind":"arxiv","id":"2606.18837","version":1},"attestation_state":"computed","paper":{"title":"Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Chengwei Qin, Hehai Lin, Qi Yang","submitted_at":"2026-06-17T09:12:50Z","abstract_excerpt":"Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To bridge this gap, we propose Skill-MAS, a novel third path t"},"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":"2606.18837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-06-17T09:12:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2a8b3362f804f228e142d541529e7d245ee331dcf686514cbef00418242e8e7e","abstract_canon_sha256":"c758a22a53ed6a88cae133d61ea9be4e65922a0bd684571ebb3172610ba1f6fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:48.859181Z","signature_b64":"+wzlmOdbC1Bzm7JL7APywKcA8WMbtau7KirZuqho15+vukVpvuJbfXRqXiwGbEf4AXGuJ+Yj+KgeUpkAjPB4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57390da31146749645a0f74b63e732081dddeb6ac76348db5c821d9229bf2a27","last_reissued_at":"2026-06-19T16:11:48.858782Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:48.858782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Chengwei Qin, Hehai Lin, Qi Yang","submitted_at":"2026-06-17T09:12:50Z","abstract_excerpt":"Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To bridge this gap, we propose Skill-MAS, a novel third path t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18837","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/2606.18837/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":"2606.18837","created_at":"2026-06-19T16:11:48.858844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18837v1","created_at":"2026-06-19T16:11:48.858844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18837","created_at":"2026-06-19T16:11:48.858844+00:00"},{"alias_kind":"pith_short_12","alias_value":"K44Q3IYRIZ2J","created_at":"2026-06-19T16:11:48.858844+00:00"},{"alias_kind":"pith_short_16","alias_value":"K44Q3IYRIZ2JMRNA","created_at":"2026-06-19T16:11:48.858844+00:00"},{"alias_kind":"pith_short_8","alias_value":"K44Q3IYR","created_at":"2026-06-19T16:11:48.858844+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/K44Q3IYRIZ2JMRNA65FWHZZSBA","json":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA.json","graph_json":"https://pith.science/api/pith-number/K44Q3IYRIZ2JMRNA65FWHZZSBA/graph.json","events_json":"https://pith.science/api/pith-number/K44Q3IYRIZ2JMRNA65FWHZZSBA/events.json","paper":"https://pith.science/paper/K44Q3IYR"},"agent_actions":{"view_html":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA","download_json":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA.json","view_paper":"https://pith.science/paper/K44Q3IYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18837&json=true","fetch_graph":"https://pith.science/api/pith-number/K44Q3IYRIZ2JMRNA65FWHZZSBA/graph.json","fetch_events":"https://pith.science/api/pith-number/K44Q3IYRIZ2JMRNA65FWHZZSBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA/action/storage_attestation","attest_author":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA/action/author_attestation","sign_citation":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA/action/citation_signature","submit_replication":"https://pith.science/pith/K44Q3IYRIZ2JMRNA65FWHZZSBA/action/replication_record"}},"created_at":"2026-06-19T16:11:48.858844+00:00","updated_at":"2026-06-19T16:11:48.858844+00:00"}