{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N6X5NJAQXVKU4NJIBKS3M2WGWJ","short_pith_number":"pith:N6X5NJAQ","schema_version":"1.0","canonical_sha256":"6fafd6a410bd554e35280aa5b66ac6b27de84f26953987a4032170700cf41d8c","source":{"kind":"arxiv","id":"2401.02051","version":3},"attestation_state":"computed","paper":{"title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Fei Liu, Fu Luo, Mingxuan Yuan, Qingfu Zhang, Xialiang Tong, Xi Lin, Zhenkun Wang, Zhichao Lu","submitted_at":"2024-01-04T04:11:59Z","abstract_excerpt":"Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an e"},"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":"2401.02051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T04:11:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d39f37c01eddf6dc6c775b5db54cec30375725bdd33e47880271a1a7d0353c3a","abstract_canon_sha256":"dacca7f3786c9c8fe77a1acb96764fb6e2050e107e86a56f6a432fa0e00027eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:51.584851Z","signature_b64":"WYVHpMAKFStltfJuKUTflNYM5NBdAsZyOxWXd0J0w/f8WFJl5yikuwzEPdTG1/0tZfgTI2R3gYaRcynROpxRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fafd6a410bd554e35280aa5b66ac6b27de84f26953987a4032170700cf41d8c","last_reissued_at":"2026-07-05T08:25:51.584395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:51.584395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Fei Liu, Fu Luo, Mingxuan Yuan, Qingfu Zhang, Xialiang Tong, Xi Lin, Zhenkun Wang, Zhichao Lu","submitted_at":"2024-01-04T04:11:59Z","abstract_excerpt":"Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02051","kind":"arxiv","version":3},"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/2401.02051/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":"2401.02051","created_at":"2026-07-05T08:25:51.584461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02051v3","created_at":"2026-07-05T08:25:51.584461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02051","created_at":"2026-07-05T08:25:51.584461+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6X5NJAQXVKU","created_at":"2026-07-05T08:25:51.584461+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6X5NJAQXVKU4NJI","created_at":"2026-07-05T08:25:51.584461+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6X5NJAQ","created_at":"2026-07-05T08:25:51.584461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07663","citing_title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","ref_index":163,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20847","citing_title":"LLM-Driven Heuristic Frame-Level Quantization Parameter Adaptation for VVenC","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20142","citing_title":"RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19741","citing_title":"Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14202","citing_title":"MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10294","citing_title":"LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25246","citing_title":"FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14202","citing_title":"MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30961","citing_title":"EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17137","citing_title":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18692","citing_title":"Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15308","citing_title":"SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29908","citing_title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03705","citing_title":"TransGP: Task-Conditioned Transformer-Guided Genetic Programming for Multitask Dynamic Flexible Job Shop Scheduling","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08083","citing_title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12421","citing_title":"Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03339","citing_title":"Automated Large-scale CVRP Solver Design via LLM-assisted Flexible MCTS","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08756","citing_title":"AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10598","citing_title":"Budget-Efficient Automatic Algorithm Design via Code Graph","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05701","citing_title":"Inference-Time Budget Control for LLM Search Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08083","citing_title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07214","citing_title":"HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05587","citing_title":"ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13131","citing_title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15001","citing_title":"COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ","json":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ.json","graph_json":"https://pith.science/api/pith-number/N6X5NJAQXVKU4NJIBKS3M2WGWJ/graph.json","events_json":"https://pith.science/api/pith-number/N6X5NJAQXVKU4NJIBKS3M2WGWJ/events.json","paper":"https://pith.science/paper/N6X5NJAQ"},"agent_actions":{"view_html":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ","download_json":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ.json","view_paper":"https://pith.science/paper/N6X5NJAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02051&json=true","fetch_graph":"https://pith.science/api/pith-number/N6X5NJAQXVKU4NJIBKS3M2WGWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/N6X5NJAQXVKU4NJIBKS3M2WGWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ/action/storage_attestation","attest_author":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ/action/author_attestation","sign_citation":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ/action/citation_signature","submit_replication":"https://pith.science/pith/N6X5NJAQXVKU4NJIBKS3M2WGWJ/action/replication_record"}},"created_at":"2026-07-05T08:25:51.584461+00:00","updated_at":"2026-07-05T08:25:51.584461+00:00"}