Pith Number

pith:34EIGVDP

pith:2023:34EIGVDPISHHSKQRF57ACMSVLE

not attested not anchored not stored refs resolved

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Bei Li, Guoqing Liu, Jiang Bian, Junliang Guo, Kaitao Song, Qingyan Guo, Rui Wang, Xu Tan, Yujiu Yang

EvoPrompt uses LLMs as evolutionary operators to automatically refine prompts and beat human designs by up to 25 percent on hard benchmarks.

arxiv:2309.08532 v3 · 2023-09-15 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{34EIGVDPISHHSKQRF57ACMSVLE}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation (e.g., up to 25% on BBH).

C2weakest 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.

C3one 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.

References

153 extracted · 153 resolved · 8 Pith anchors

[1] Asset: A dataset for tuning and evaluation of sentence simplification models with multiple rewriting transformations 2020

[2] Promptsource: An integrated development environment and repository for natural language prompts 2022

[3] Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems 2006

[4] Language models are few-shot learners 1901

[6] Introduction to derivative-free optimization 2009

Formal links

2 machine-checked theorem links

Cited by

31 papers in Pith

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

Receipt and verification

First computed	2026-05-17T23:38:48.874329Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

df0883546f448e792a112f7e0132555929cb85eab255ab70cb9d0cc4a08d53eb

Aliases

arxiv: 2309.08532 · arxiv_version: 2309.08532v3 · doi: 10.48550/arxiv.2309.08532 · pith_short_12: 34EIGVDPISHH · pith_short_16: 34EIGVDPISHHSKQR · pith_short_8: 34EIGVDP

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/34EIGVDPISHHSKQRF57ACMSVLE \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: df0883546f448e792a112f7e0132555929cb85eab255ab70cb9d0cc4a08d53eb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2619070d2d25f0a47bd5837141180c0a5938f3c5883f0b1d5b8f57f6b16c3148",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-09-15T16:50:09Z",
    "title_canon_sha256": "174d00ad83c4d3ecc6a4a236a8f78a23dee074fdfdc67694d1ed633f9f15383e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2309.08532",
    "kind": "arxiv",
    "version": 3
  }
}