Pith Number

pith:YKCLRBMG

pith:2024:YKCLRBMGAWNJATFOD2E5WVPH5J

not attested not anchored not stored refs resolved

AFlow: Automating Agentic Workflow Generation

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

Code search automates LLM workflows with 5.7% performance gains

arxiv:2410.10762 v4 · 2024-10-14 · cs.AI · cs.CL · cs.LG · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YKCLRBMGAWNJATFOD2E5WVPH5J}

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

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.

C2weakest 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.

C3one 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.

References

63 extracted · 63 resolved · 0 Pith anchors

[1] Begin with a clear statement of the problem

[2] Explain the approach and any formulas or concepts used

[3] Show step-by-step calculations, using LaTeX notation for mathematical expressions

[4] Interpret the code output and incorporate it into your explanation

[5] Provide a final answer, enclosed in \boxed{} LaTeX notation

Cited by

40 papers in Pith

Language Model Networks: Supervision-Efficient Learning through Dense Communication

Towards Direct Evaluation of Harness Optimizers via Priority Ranking

Self-Evolving Multi-Agent Systems via Decentralized Memory

Harnesses for Inference-Time Alignment over Execution Trajectories

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis

Receipt and verification

First computed	2026-05-17T23:38:53.710970Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c284b88586059a904cae1e89db55e7ea7fdaebbf020f5c448eda793350db32f2

Aliases

arxiv: 2410.10762 · arxiv_version: 2410.10762v4 · doi: 10.48550/arxiv.2410.10762 · pith_short_12: YKCLRBMGAWNJ · pith_short_16: YKCLRBMGAWNJATFO · pith_short_8: YKCLRBMG

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/YKCLRBMGAWNJATFOD2E5WVPH5J \
  | 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: c284b88586059a904cae1e89db55e7ea7fdaebbf020f5c448eda793350db32f2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "72af6de20abb7dc257f29c7597c88f76e2bd17da4d30c49ebc056dedd4e90844",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG",
      "cs.SE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2024-10-14T17:40:40Z",
    "title_canon_sha256": "6eb98f7dbf700f1f4bf1aa30b3fe0fd739e9e61c275405e38de7f12aaab23c98"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.10762",
    "kind": "arxiv",
    "version": 4
  }
}