{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:34EIGVDPISHHSKQRF57ACMSVLE","short_pith_number":"pith:34EIGVDP","schema_version":"1.0","canonical_sha256":"df0883546f448e792a112f7e0132555929cb85eab255ab70cb9d0cc4a08d53eb","source":{"kind":"arxiv","id":"2309.08532","version":3},"attestation_state":"computed","paper":{"title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EvoPrompt uses LLMs as evolutionary operators to automatically refine prompts and beat human designs by up to 25 percent on hard benchmarks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Li, Guoqing Liu, Jiang Bian, Junliang Guo, Kaitao Song, Qingyan Guo, Rui Wang, Xu Tan, Yujiu Yang","submitted_at":"2023-09-15T16:50:09Z","abstract_excerpt":"Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization, called EvoPrompt, which borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence. To enable EAs to work on discrete prompts, which are natural language expressions that need to be coherent and human-readable, we connect LLMs with EAs. This approach allows us to simultaneously leverage the powerful language p"},"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":"2309.08532","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T16:50:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"174d00ad83c4d3ecc6a4a236a8f78a23dee074fdfdc67694d1ed633f9f15383e","abstract_canon_sha256":"2619070d2d25f0a47bd5837141180c0a5938f3c5883f0b1d5b8f57f6b16c3148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.874920Z","signature_b64":"M7FpEd1tCrVQkXSO/56vo16d/jE54mw1UTAglVk4JMiS50vvzmYZmv7hSHqKyE/hfXrAbmXUTDMDEBTLaOHuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df0883546f448e792a112f7e0132555929cb85eab255ab70cb9d0cc4a08d53eb","last_reissued_at":"2026-05-17T23:38:48.874329Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.874329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EvoPrompt uses LLMs as evolutionary operators to automatically refine prompts and beat human designs by up to 25 percent on hard benchmarks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Li, Guoqing Liu, Jiang Bian, Junliang Guo, Kaitao Song, Qingyan Guo, Rui Wang, Xu Tan, Yujiu Yang","submitted_at":"2023-09-15T16:50:09Z","abstract_excerpt":"Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization, called EvoPrompt, which borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence. To enable EAs to work on discrete prompts, which are natural language expressions that need to be coherent and human-readable, we connect LLMs with EAs. This approach allows us to simultaneously leverage the powerful language p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation (e.g., up to 25% on BBH).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs can reliably generate coherent, human-readable prompts when acting as evolutionary operators (crossover, mutation) without introducing inconsistencies or quality drift across iterations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EvoPrompt uses LLMs as evolutionary operators to automatically refine prompts and beat human designs by up to 25 percent on hard benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a1bcdcd453334b363c44673ba5ae3d825e0b8bcfd9471b8ab3d67d0bf4dd7c58"},"source":{"id":"2309.08532","kind":"arxiv","version":3},"verdict":{"id":"f1413506-22cb-4b64-b700-c9c68db50e65","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:08:22.712798Z","strongest_claim":"EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation (e.g., up to 25% on BBH).","one_line_summary":"EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs can reliably generate coherent, human-readable prompts when acting as evolutionary operators (crossover, mutation) without introducing inconsistencies or quality drift across iterations.","pith_extraction_headline":"EvoPrompt uses LLMs as evolutionary operators to automatically refine prompts and beat human designs by up to 25 percent on hard benchmarks."},"references":{"count":153,"sample":[{"doi":"","year":2020,"title":"Asset: A dataset for tuning and evaluation of sentence simplification models with multiple rewriting transformations","work_id":"00cae906-46c9-4c98-a9f7-17eb167406fe","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Promptsource: An integrated development environment and repository for natural language prompts","work_id":"4bf53595-bad7-407f-b926-8a5843b75ed2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems","work_id":"06670735-31dd-4d65-989a-6d0a20b9cb06","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"b5af3a68-2622-4421-b39b-b1d2fbde2d8d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Introduction to derivative-free optimization","work_id":"7a9b1aac-3f7d-4d23-8717-f38597a33b8e","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":153,"snapshot_sha256":"6cd30c4fa6464426d7dcdf23bd274c790a541d5fa41faa7027605d10c56b8866","internal_anchors":8},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5423d637a46f2e399a4c65a9a8ec99542fee27284abde21da0feacd309cbd034"},"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":"2309.08532","created_at":"2026-05-17T23:38:48.874447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08532v3","created_at":"2026-05-17T23:38:48.874447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08532","created_at":"2026-05-17T23:38:48.874447+00:00"},{"alias_kind":"pith_short_12","alias_value":"34EIGVDPISHH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"34EIGVDPISHHSKQR","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"34EIGVDP","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":31,"sample":[{"citing_arxiv_id":"2503.14434","citing_title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21318","citing_title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15177","citing_title":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15721","citing_title":"Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16233","citing_title":"FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19102","citing_title":"Prompt Optimization for LLM Code Generation via Reinforcement Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19330","citing_title":"MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08332","citing_title":"ORFS-agent: Tool-Using Agents for Chip Design Optimization","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.25223","citing_title":"FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2512.08984","citing_title":"RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2601.20981","citing_title":"Diversifying Toxicity Search in Large Language Models Through Speciation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13874","citing_title":"GEAR: Genetic AutoResearch for Agentic Code Evolution","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12484","citing_title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15177","citing_title":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2309.03409","citing_title":"Large Language Models as Optimizers","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06061","citing_title":"PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12484","citing_title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08769","citing_title":"EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04107","citing_title":"TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21950","citing_title":"Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12616","citing_title":"Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10734","citing_title":"Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06566","citing_title":"AI-Driven Research for Databases","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE","json":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE.json","graph_json":"https://pith.science/api/pith-number/34EIGVDPISHHSKQRF57ACMSVLE/graph.json","events_json":"https://pith.science/api/pith-number/34EIGVDPISHHSKQRF57ACMSVLE/events.json","paper":"https://pith.science/paper/34EIGVDP"},"agent_actions":{"view_html":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE","download_json":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE.json","view_paper":"https://pith.science/paper/34EIGVDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08532&json=true","fetch_graph":"https://pith.science/api/pith-number/34EIGVDPISHHSKQRF57ACMSVLE/graph.json","fetch_events":"https://pith.science/api/pith-number/34EIGVDPISHHSKQRF57ACMSVLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE/action/storage_attestation","attest_author":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE/action/author_attestation","sign_citation":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE/action/citation_signature","submit_replication":"https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE/action/replication_record"}},"created_at":"2026-05-17T23:38:48.874447+00:00","updated_at":"2026-05-17T23:38:48.874447+00:00"}