{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TWCXKMGLPAGS4U2C6XC45WTX2","short_pith_number":"pith:2TWCXKMG","schema_version":"1.0","canonical_sha256":"d4ec2ba9865bc069729a17ae2e76d3be974978183d21d62dea6e18089d58edd6","source":{"kind":"arxiv","id":"2410.11163","version":2},"attestation_state":"computed","paper":{"title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achin Kulshrestha, Chen-Yu Lee, Hamid Palangi, Lesly Miculicich, Nathalie Rauschmayr, Sayna Ebrahimi, Shangbin Feng, Tomas Pfister, Yejin Choi, Yike Wang, Yulia Tsvetkov, Zifeng Wang","submitted_at":"2024-10-15T00:59:17Z","abstract_excerpt":"We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, Model Swarms offers tuning-free model adaptation, works in low-data regimes with as few as 200 examples, and does not require ass"},"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":"2410.11163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T00:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"62ad5822683bb87ced71436383c7c178108ae34cd776662687c9e4cd4ea50e8d","abstract_canon_sha256":"12ef021e77d40cd2a8762554d811f7714d7b774e081ea97b850c779bb083d393"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:14.146148Z","signature_b64":"d6Jv4uf7xs+I3V2/EnP1t5vdhpyC0RNSqQByUREVC8pgZnKSt7VAAxFPb1XhjCXfLf9llFBKJujvdGZ+m2uwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4ec2ba9865bc069729a17ae2e76d3be974978183d21d62dea6e18089d58edd6","last_reissued_at":"2026-07-05T11:13:14.145348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:14.145348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achin Kulshrestha, Chen-Yu Lee, Hamid Palangi, Lesly Miculicich, Nathalie Rauschmayr, Sayna Ebrahimi, Shangbin Feng, Tomas Pfister, Yejin Choi, Yike Wang, Yulia Tsvetkov, Zifeng Wang","submitted_at":"2024-10-15T00:59:17Z","abstract_excerpt":"We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, Model Swarms offers tuning-free model adaptation, works in low-data regimes with as few as 200 examples, and does not require ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11163","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/2410.11163/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":"2410.11163","created_at":"2026-07-05T11:13:14.145449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11163v2","created_at":"2026-07-05T11:13:14.145449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11163","created_at":"2026-07-05T11:13:14.145449+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TWCXKMGLPAG","created_at":"2026-07-05T11:13:14.145449+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TWCXKMGLPAGS4U2","created_at":"2026-07-05T11:13:14.145449+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TWCXKMG","created_at":"2026-07-05T11:13:14.145449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18535","citing_title":"Beyond Scaling: Agents Are Heading to the Edge","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15972","citing_title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2","json":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2.json","graph_json":"https://pith.science/api/pith-number/2TWCXKMGLPAGS4U2C6XC45WTX2/graph.json","events_json":"https://pith.science/api/pith-number/2TWCXKMGLPAGS4U2C6XC45WTX2/events.json","paper":"https://pith.science/paper/2TWCXKMG"},"agent_actions":{"view_html":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2","download_json":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2.json","view_paper":"https://pith.science/paper/2TWCXKMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11163&json=true","fetch_graph":"https://pith.science/api/pith-number/2TWCXKMGLPAGS4U2C6XC45WTX2/graph.json","fetch_events":"https://pith.science/api/pith-number/2TWCXKMGLPAGS4U2C6XC45WTX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2/action/storage_attestation","attest_author":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2/action/author_attestation","sign_citation":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2/action/citation_signature","submit_replication":"https://pith.science/pith/2TWCXKMGLPAGS4U2C6XC45WTX2/action/replication_record"}},"created_at":"2026-07-05T11:13:14.145449+00:00","updated_at":"2026-07-05T11:13:14.145449+00:00"}