{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LUOGLLASVK43SCRYXSJGT243GB","short_pith_number":"pith:LUOGLLAS","schema_version":"1.0","canonical_sha256":"5d1c65ac12aab9b90a38bc9269eb9b307b37bcdc4b21ec2649f9c1a6f9634677","source":{"kind":"arxiv","id":"2408.08435","version":2},"attestation_state":"computed","paper":{"title":"Automated Design of Agentic Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A meta-agent can program new agents in code that outperform hand-designed ones and transfer across domains.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cong Lu, Jeff Clune, Shengran Hu","submitted_at":"2024-08-15T21:59:23Z","abstract_excerpt":"Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine learning teaches us that hand-designed solutions are eventually replaced by learned solutions. We describe a newly forming research area, Automated Design of Agentic Systems (ADAS), which aims to automatically create powerful agentic system designs, including inventing novel building blocks and/or combining them in new ways. We further demonstrate tha"},"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":"2408.08435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-15T21:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"39006fd75159d83b2f62f511b693c2d1ab14e255800e1fb3331ee7bc06cba4be","abstract_canon_sha256":"8db6332235ff2e9fda484dbfc136fab44fc292aa1ed0294d556aa480bfa1d2b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.065356Z","signature_b64":"aR48idS6pfSKTjeviKgBQ2OotIc/Cz2q+/Nsf8A0Ih8l17UKvbcdBCmR0SLA/XZnqLpaCWQYsVUAA+E8/uVfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d1c65ac12aab9b90a38bc9269eb9b307b37bcdc4b21ec2649f9c1a6f9634677","last_reissued_at":"2026-05-17T23:38:53.064734Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.064734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Design of Agentic Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A meta-agent can program new agents in code that outperform hand-designed ones and transfer across domains.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cong Lu, Jeff Clune, Shengran Hu","submitted_at":"2024-08-15T21:59:23Z","abstract_excerpt":"Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine learning teaches us that hand-designed solutions are eventually replaced by learned solutions. We describe a newly forming research area, Automated Design of Agentic Systems (ADAS), which aims to automatically create powerful agentic system designs, including inventing novel building blocks and/or combining them in new ways. We further demonstrate tha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through extensive experiments across multiple domains including coding, science, and math, we show that our algorithm can progressively invent agents with novel designs that greatly outperform state-of-the-art hand-designed agents. Importantly, we consistently observe the surprising result that agents invented by Meta Agent Search maintain superior performance even when transferred across domains and models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The meta-agent can reliably generate functional, non-trivial new agent code from the archive without the search becoming dominated by ineffective or hallucinated programs, and that performance gains on the tested tasks reflect genuine improvements rather than overfitting to the evaluation setup.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A meta-agent can program new agents in code that outperform hand-designed ones and transfer across domains.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c33b1871f07524ab761e9bffb9ce58b91d078ea51102f8ca6290f03df01bd9e3"},"source":{"id":"2408.08435","kind":"arxiv","version":2},"verdict":{"id":"f89bf277-13be-4d72-9192-fdebae510621","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:03:09.049437Z","strongest_claim":"Through extensive experiments across multiple domains including coding, science, and math, we show that our algorithm can progressively invent agents with novel designs that greatly outperform state-of-the-art hand-designed agents. Importantly, we consistently observe the surprising result that agents invented by Meta Agent Search maintain superior performance even when transferred across domains and models.","one_line_summary":"Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The meta-agent can reliably generate functional, non-trivial new agent code from the archive without the search becoming dominated by ineffective or hallucinated programs, and that performance gains on the tested tasks reflect genuine improvements rather than overfitting to the evaluation setup.","pith_extraction_headline":"A meta-agent can program new agents in code that outperform hand-designed ones and transfer across domains."},"references":{"count":208,"sample":[{"doi":"","year":null,"title":"Journal of Machine Learning Research , volume=","work_id":"624d20f4-9b7f-40ba-9536-7fdb2809375e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"International Conference on Machine Learning , pages=","work_id":"2a811334-3665-4f71-85af-e2a971e08c1d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"d8806a86-45c1-4d37-80a1-89ed680f9e17","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Autoagents: A framework for automatic agent generation","work_id":"6863e6b9-5143-4d8c-b7a2-276625d012f5","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Forty-first International Conference on Machine Learning , year=","work_id":"2f445f15-0b75-490e-b5b9-01572e15f1de","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":208,"snapshot_sha256":"af74acfc2b9c6af9ecf80826e6a249911e72aba2618ffadca9b060afb9e0e20e","internal_anchors":20},"formal_canon":{"evidence_count":2,"snapshot_sha256":"317b30ad6bb3c205d4d0758c2ea8d1cedbc085fcd34f1cdc74c79c8356a7940b"},"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":"2408.08435","created_at":"2026-05-17T23:38:53.064834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08435v2","created_at":"2026-05-17T23:38:53.064834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08435","created_at":"2026-05-17T23:38:53.064834+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUOGLLASVK43","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUOGLLASVK43SCRY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUOGLLAS","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":39,"internal_anchor_count":39,"sample":[{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21347","citing_title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22505","citing_title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21516","citing_title":"Harnesses for Inference-Time Alignment over Execution Trajectories","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20425","citing_title":"AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21347","citing_title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17361","citing_title":"\\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19140","citing_title":"Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19633","citing_title":"optimize_anything: A Universal API for Optimizing any Text Parameter","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2506.10060","citing_title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2509.19349","citing_title":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","ref_index":219,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15599","citing_title":"Autonomous Business System via Neuro-symbolic AI","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15232","citing_title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16322","citing_title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14483","citing_title":"LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":276,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13647","citing_title":"FlowCompile: An Optimizing Compiler for Structured LLM Workflows","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13821","citing_title":"Harnessing Agentic Evolution","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02988","citing_title":"Self-Optimizing Multi-Agent Systems for Deep Research","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08083","citing_title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27221","citing_title":"Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB","json":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB.json","graph_json":"https://pith.science/api/pith-number/LUOGLLASVK43SCRYXSJGT243GB/graph.json","events_json":"https://pith.science/api/pith-number/LUOGLLASVK43SCRYXSJGT243GB/events.json","paper":"https://pith.science/paper/LUOGLLAS"},"agent_actions":{"view_html":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB","download_json":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB.json","view_paper":"https://pith.science/paper/LUOGLLAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08435&json=true","fetch_graph":"https://pith.science/api/pith-number/LUOGLLASVK43SCRYXSJGT243GB/graph.json","fetch_events":"https://pith.science/api/pith-number/LUOGLLASVK43SCRYXSJGT243GB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB/action/storage_attestation","attest_author":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB/action/author_attestation","sign_citation":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB/action/citation_signature","submit_replication":"https://pith.science/pith/LUOGLLASVK43SCRYXSJGT243GB/action/replication_record"}},"created_at":"2026-05-17T23:38:53.064834+00:00","updated_at":"2026-05-17T23:38:53.064834+00:00"}