{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKCLRBMGAWNJATFOD2E5WVPH5J","short_pith_number":"pith:YKCLRBMG","schema_version":"1.0","canonical_sha256":"c284b88586059a904cae1e89db55e7ea7fdaebbf020f5c448eda793350db32f2","source":{"kind":"arxiv","id":"2410.10762","version":4},"attestation_state":"computed","paper":{"title":"AFlow: Automating Agentic Workflow Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Code search automates LLM workflows with 5.7% performance gains","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Bingnan Zheng, Chenglin Wu, Fengwei Teng, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Jinyu Xiang, Mingchen Zhuge, Sirui Hong, Xin Cheng, Xionghui Chen, Yuyu Luo, Zhaoyang Yu","submitted_at":"2024-10-14T17:40:40Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformula"},"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":false},"canonical_record":{"source":{"id":"2410.10762","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T17:40:40Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"6eb98f7dbf700f1f4bf1aa30b3fe0fd739e9e61c275405e38de7f12aaab23c98","abstract_canon_sha256":"72af6de20abb7dc257f29c7597c88f76e2bd17da4d30c49ebc056dedd4e90844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.711486Z","signature_b64":"eiLIBpMhCEicThvW1QXykLWXT0FMqUSIFaBaL6c2C5gpEfcppcuLyjlPpEkQU4O2mSUdFTXlgWLswgJq7gxkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c284b88586059a904cae1e89db55e7ea7fdaebbf020f5c448eda793350db32f2","last_reissued_at":"2026-05-17T23:38:53.710970Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.710970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AFlow: Automating Agentic Workflow Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Code search automates LLM workflows with 5.7% performance gains","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Bingnan Zheng, Chenglin Wu, Fengwei Teng, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Jinyu Xiang, Mingchen Zhuge, Sirui Hong, Xin Cheng, Xionghui Chen, Yuyu Luo, Zhaoyang Yu","submitted_at":"2024-10-14T17:40:40Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformula"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the space of code-represented workflows can be searched efficiently by Monte Carlo Tree Search with code edits and execution feedback without excessive compute or getting trapped in poor local solutions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AFlow uses Monte Carlo Tree Search to automatically generate and optimize code-represented agentic workflows for LLMs, delivering a 5.7% average gain over prior methods on six benchmarks while letting smaller models beat GPT-4o at low cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Code search automates LLM workflows with 5.7% performance gains","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0aaf50ab712c6c228e94e46992b94fd2887474d1e05ade4ddcd7ce47e5ba4d57"},"source":{"id":"2410.10762","kind":"arxiv","version":4},"verdict":{"id":"e6ec8376-b1fd-45c9-9091-7193e3d29296","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:04:59.474821Z","strongest_claim":"Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars.","one_line_summary":"AFlow uses Monte Carlo Tree Search to automatically generate and optimize code-represented agentic workflows for LLMs, delivering a 5.7% average gain over prior methods on six benchmarks while letting smaller models beat GPT-4o at low cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the space of code-represented workflows can be searched efficiently by Monte Carlo Tree Search with code edits and execution feedback without excessive compute or getting trapped in poor local solutions.","pith_extraction_headline":"Code search automates LLM workflows with 5.7% performance gains"},"references":{"count":63,"sample":[{"doi":"","year":null,"title":"Begin with a clear statement of the problem","work_id":"88d279aa-f22f-4edd-afab-f3757a169a9d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Explain the approach and any formulas or concepts used","work_id":"3eed3c13-e959-4090-bb89-40335b4408af","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Show step-by-step calculations, using LaTeX notation for mathematical expressions","work_id":"a5391493-0aa2-46f3-b9c6-ee1c779ba31f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Interpret the code output and incorporate it into your explanation","work_id":"70551d31-5799-4a4d-bbf8-a07e0d209706","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Provide a final answer, enclosed in \\boxed{} LaTeX notation","work_id":"ce8747c0-b767-4176-8d73-1d34120ec720","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":63,"snapshot_sha256":"25618a8bdc6c9d4d2ee00612c9913f454216a684cc75959cbf7224a8e9ae831c","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":"2410.10762","created_at":"2026-05-17T23:38:53.711055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10762v4","created_at":"2026-05-17T23:38:53.711055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10762","created_at":"2026-05-17T23:38:53.711055+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKCLRBMGAWNJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKCLRBMGAWNJATFO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKCLRBMG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":40,"internal_anchor_count":40,"sample":[{"citing_arxiv_id":"2505.12741","citing_title":"Language Model Networks: Supervision-Efficient Learning through Dense Communication","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22505","citing_title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22721","citing_title":"Self-Evolving Multi-Agent Systems via Decentralized Memory","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21516","citing_title":"Harnesses for Inference-Time Alignment over Execution Trajectories","ref_index":38,"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":156,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07799","citing_title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20425","citing_title":"AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03409","citing_title":"Robust Agent Compensation (RAC): Teaching AI Agents to Compensate","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18597","citing_title":"Latent Action Reparameterization for Efficient Agent Inference","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18181","citing_title":"Scalable Environments Drive Generalizable Agents","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19140","citing_title":"Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19633","citing_title":"optimize_anything: A Universal API for Optimizing any Text Parameter","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2506.00886","citing_title":"Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2512.18746","citing_title":"MemEvolve: Meta-Evolution of Agent Memory Systems","ref_index":33,"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":188,"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":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09608","citing_title":"Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04942","citing_title":"TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14483","citing_title":"LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":62,"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":275,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13647","citing_title":"FlowCompile: An Optimizing Compiler for Structured LLM Workflows","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13821","citing_title":"Harnessing Agentic Evolution","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28052","citing_title":"Meta-Harness: End-to-End Optimization of Model Harnesses","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J","json":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J.json","graph_json":"https://pith.science/api/pith-number/YKCLRBMGAWNJATFOD2E5WVPH5J/graph.json","events_json":"https://pith.science/api/pith-number/YKCLRBMGAWNJATFOD2E5WVPH5J/events.json","paper":"https://pith.science/paper/YKCLRBMG"},"agent_actions":{"view_html":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J","download_json":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J.json","view_paper":"https://pith.science/paper/YKCLRBMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10762&json=true","fetch_graph":"https://pith.science/api/pith-number/YKCLRBMGAWNJATFOD2E5WVPH5J/graph.json","fetch_events":"https://pith.science/api/pith-number/YKCLRBMGAWNJATFOD2E5WVPH5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J/action/storage_attestation","attest_author":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J/action/author_attestation","sign_citation":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J/action/citation_signature","submit_replication":"https://pith.science/pith/YKCLRBMGAWNJATFOD2E5WVPH5J/action/replication_record"}},"created_at":"2026-05-17T23:38:53.711055+00:00","updated_at":"2026-05-17T23:38:53.711055+00:00"}