{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H5E4RBVVO73D2O55WUITJ4EDRU","short_pith_number":"pith:H5E4RBVV","schema_version":"1.0","canonical_sha256":"3f49c886b577f63d3bbdb51134f0838d18b7c4e248340dd84ac6f9815680cecb","source":{"kind":"arxiv","id":"2502.13138","version":1},"attestation_state":"computed","paper":{"title":"AIDE: AI-Driven Exploration in the Space of Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Deniss Jacenko, Dhruv Srikanth, Dixing Xu, Dominik Schmidt, Ian Kaplan, Yuxiang WU, Zhengyao Jiang","submitted_at":"2025-02-18T18:57:21Z","abstract_excerpt":"Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2502.13138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T18:57:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12ed0c321dfb54715b553cf42ff7c0ef45beb36bcedadc170f2de58489f2b47a","abstract_canon_sha256":"f5fb737c5d0d23c7b616c2709def8648acee758a13af530cf04429ab1ad9f46c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.411341Z","signature_b64":"R59m3jBOtLNMdT0Wq6Ir2u42hlO8hyE8UD8qP4oWdUza/WiInzRzDY3iVUOitnqk5M70tNAl21jLhxLDn3MOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f49c886b577f63d3bbdb51134f0838d18b7c4e248340dd84ac6f9815680cecb","last_reissued_at":"2026-05-17T23:38:13.410583Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.410583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIDE: AI-Driven Exploration in the Space of Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Deniss Jacenko, Dhruv Srikanth, Dixing Xu, Dominik Schmidt, Ian Kaplan, Yuxiang WU, Zhengyao Jiang","submitted_at":"2025-02-18T18:57:21Z","abstract_excerpt":"Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the tree search guided by LLMs can reliably identify and improve upon promising code variants without the search space becoming intractable or the evaluations becoming unreliable.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"a7a736928e39dd1d21318f06b558abc94b39c80ce541c3a3920bfa620a4dd389"},"source":{"id":"2502.13138","kind":"arxiv","version":1},"verdict":{"id":"7ba5a638-9b0b-4040-9396-88e88438a4cd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T18:16:23.603996Z","strongest_claim":"By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.","one_line_summary":"AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the tree search guided by LLMs can reliably identify and improve upon promising code variants without the search space becoming intractable or the evaluations becoming unreliable.","pith_extraction_headline":""},"references":{"count":14,"sample":[{"doi":"10.1126/science.abq1158","year":2019,"title":"Li, Y., Choi, D.H., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., et al., 2022","work_id":"cc452f34-3d34-41ff-9206-8edad6625ce6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","ref_index":2,"cited_arxiv_id":"2305.16291","is_internal_anchor":true},{"doi":"","year":null,"title":"Distributed Random Forest (DRF) and Extremely Randomized Trees (XRT)","work_id":"db2145b6-e1e8-4ce3-a44c-c900ebb7293f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Generalized Linear Model (GLM) with regularization","work_id":"f095d396-55ea-4ee6-b3d3-89474fcae80e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"H2O Gradient Boosting Machines","work_id":"89aee919-4405-4246-bae7-3854966a8126","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"098c479e261841ca43a655028e78ffc90d602a830a9ea7264f463b467e7ac2fc","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c0441559ff1bf371acd3626b67e14ca2eb2fc1ccc17cfc5cba518557fcd889d9"},"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":"2502.13138","created_at":"2026-05-17T23:38:13.410691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13138v1","created_at":"2026-05-17T23:38:13.410691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13138","created_at":"2026-05-17T23:38:13.410691+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5E4RBVVO73D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5E4RBVVO73D2O55","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5E4RBVV","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2602.13473","citing_title":"NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22878","citing_title":"SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.23986","citing_title":"TusoAI: Agentic Optimization for Scientific Methods","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21384","citing_title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11518","citing_title":"AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16616","citing_title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17373","citing_title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17539","citing_title":"Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20025","citing_title":"AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20086","citing_title":"What Do Evolutionary Coding Agents Evolve?","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15461","citing_title":"DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2509.19349","citing_title":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","ref_index":223,"is_internal_anchor":true},{"citing_arxiv_id":"2602.07906","citing_title":"AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01692","citing_title":"Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14869","citing_title":"A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13874","citing_title":"GEAR: Genetic AutoResearch for Agentic Code Evolution","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2603.26499","citing_title":"AIRA_2: Overcoming Bottlenecks in AI Research Agents","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11518","citing_title":"AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU","json":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU.json","graph_json":"https://pith.science/api/pith-number/H5E4RBVVO73D2O55WUITJ4EDRU/graph.json","events_json":"https://pith.science/api/pith-number/H5E4RBVVO73D2O55WUITJ4EDRU/events.json","paper":"https://pith.science/paper/H5E4RBVV"},"agent_actions":{"view_html":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU","download_json":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU.json","view_paper":"https://pith.science/paper/H5E4RBVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13138&json=true","fetch_graph":"https://pith.science/api/pith-number/H5E4RBVVO73D2O55WUITJ4EDRU/graph.json","fetch_events":"https://pith.science/api/pith-number/H5E4RBVVO73D2O55WUITJ4EDRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU/action/storage_attestation","attest_author":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU/action/author_attestation","sign_citation":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU/action/citation_signature","submit_replication":"https://pith.science/pith/H5E4RBVVO73D2O55WUITJ4EDRU/action/replication_record"}},"created_at":"2026-05-17T23:38:13.410691+00:00","updated_at":"2026-05-17T23:38:13.410691+00:00"}