{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GOTGYCX7ZIPKBP2225JGWO2B2V","short_pith_number":"pith:GOTGYCX7","schema_version":"1.0","canonical_sha256":"33a66c0affca1ea0bf5ad7526b3b41d551abb8af62f379acf9c10c67dd2bce82","source":{"kind":"arxiv","id":"2410.17238","version":1},"attestation_state":"computed","paper":{"title":"SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Bangbang Liu, Bang Liu, Ceyao Zhang, Chenglin Wu, Duyi Pan, Guanghao Mei, Jacky Kwok, Sirui Hong, Tianqi Pang, Yaying Fei, Yizhang Lin, Yizhou Chi","submitted_at":"2024-10-22T17:56:08Z","abstract_excerpt":"Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents have shown promise in automating machine learning tasks, they often generate low-diversity and suboptimal code, even after multiple iterations. To overcome these limitations, we introduce Tree-Search Enhanced LLM Agents (SELA), an innovative agent-based system that leverages Monte Carlo Tree Search (MCTS) to optimize the AutoML process. By representing pipeli"},"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":"2410.17238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T17:56:08Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"98904eb89e7e5d0d4aa80e2383f90cc6a56607fcdf04d7a392950e8efefbbb3c","abstract_canon_sha256":"0c3639ad3358c20e9baf9822579194b8c6a675067c18542d6751cf7e628b4b75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:13.984387Z","signature_b64":"HqXqp8ZE0zbfm0TVWfN0qDjaPGFUnWACgTEuSotvsdQ9Pq3CdXzjLXoVYWVjAwpL2snLhGUGrdB6sVgiFD2XDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33a66c0affca1ea0bf5ad7526b3b41d551abb8af62f379acf9c10c67dd2bce82","last_reissued_at":"2026-07-05T09:24:13.983972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:13.983972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Bangbang Liu, Bang Liu, Ceyao Zhang, Chenglin Wu, Duyi Pan, Guanghao Mei, Jacky Kwok, Sirui Hong, Tianqi Pang, Yaying Fei, Yizhang Lin, Yizhou Chi","submitted_at":"2024-10-22T17:56:08Z","abstract_excerpt":"Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents have shown promise in automating machine learning tasks, they often generate low-diversity and suboptimal code, even after multiple iterations. To overcome these limitations, we introduce Tree-Search Enhanced LLM Agents (SELA), an innovative agent-based system that leverages Monte Carlo Tree Search (MCTS) to optimize the AutoML process. By representing pipeli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17238","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/2410.17238/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":"2410.17238","created_at":"2026-07-05T09:24:13.984027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17238v1","created_at":"2026-07-05T09:24:13.984027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17238","created_at":"2026-07-05T09:24:13.984027+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOTGYCX7ZIPK","created_at":"2026-07-05T09:24:13.984027+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOTGYCX7ZIPKBP22","created_at":"2026-07-05T09:24:13.984027+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOTGYCX7","created_at":"2026-07-05T09:24:13.984027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25207","citing_title":"ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21891","citing_title":"Learning the ARTS of Search for Automated Discovery","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17915","citing_title":"Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10177","citing_title":"KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20375","citing_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V","json":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V.json","graph_json":"https://pith.science/api/pith-number/GOTGYCX7ZIPKBP2225JGWO2B2V/graph.json","events_json":"https://pith.science/api/pith-number/GOTGYCX7ZIPKBP2225JGWO2B2V/events.json","paper":"https://pith.science/paper/GOTGYCX7"},"agent_actions":{"view_html":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V","download_json":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V.json","view_paper":"https://pith.science/paper/GOTGYCX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17238&json=true","fetch_graph":"https://pith.science/api/pith-number/GOTGYCX7ZIPKBP2225JGWO2B2V/graph.json","fetch_events":"https://pith.science/api/pith-number/GOTGYCX7ZIPKBP2225JGWO2B2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V/action/storage_attestation","attest_author":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V/action/author_attestation","sign_citation":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V/action/citation_signature","submit_replication":"https://pith.science/pith/GOTGYCX7ZIPKBP2225JGWO2B2V/action/replication_record"}},"created_at":"2026-07-05T09:24:13.984027+00:00","updated_at":"2026-07-05T09:24:13.984027+00:00"}