Pith Number

pith:LUOGLLAS

pith:2024:LUOGLLASVK43SCRYXSJGT243GB

not attested not anchored not stored refs resolved

Automated Design of Agentic Systems

Cong Lu, Jeff Clune, Shengran Hu

A meta-agent can program new agents in code that outperform hand-designed ones and transfer across domains.

arxiv:2408.08435 v2 · 2024-08-15 · 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{LUOGLLASVK43SCRYXSJGT243GB}

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

Through extensive experiments across multiple domains including coding, science, and math, we show that our algorithm can progressively invent agents with novel designs that greatly outperform state-of-the-art hand-designed agents. Importantly, we consistently observe the surprising result that agents invented by Meta Agent Search maintain superior performance even when transferred across domains and models.

C2weakest assumption

The meta-agent can reliably generate functional, non-trivial new agent code from the archive without the search becoming dominated by ineffective or hallucinated programs, and that performance gains on the tested tasks reflect genuine improvements rather than overfitting to the evaluation setup.

C3one line summary

Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.

References

208 extracted · 208 resolved · 20 Pith anchors

[2] Journal of Machine Learning Research , volume=

[3] International Conference on Machine Learning , pages= 2021

[5] The Twelfth International Conference on Learning Representations , year=

[6] Autoagents: A framework for automatic agent generation

[7] Forty-first International Conference on Machine Learning , year=

Formal links

2 machine-checked theorem links

Cited by

39 papers in Pith

An AI system to help scientists write expert-level empirical software

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

Towards Direct Evaluation of Harness Optimizers via Priority Ranking

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	2026-05-17T23:38:53.064734Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5d1c65ac12aab9b90a38bc9269eb9b307b37bcdc4b21ec2649f9c1a6f9634677

Aliases

arxiv: 2408.08435 · arxiv_version: 2408.08435v2 · doi: 10.48550/arxiv.2408.08435 · pith_short_12: LUOGLLASVK43 · pith_short_16: LUOGLLASVK43SCRY · pith_short_8: LUOGLLAS

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/LUOGLLASVK43SCRYXSJGT243GB \
  | 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: 5d1c65ac12aab9b90a38bc9269eb9b307b37bcdc4b21ec2649f9c1a6f9634677

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8db6332235ff2e9fda484dbfc136fab44fc292aa1ed0294d556aa480bfa1d2b4",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2024-08-15T21:59:23Z",
    "title_canon_sha256": "39006fd75159d83b2f62f511b693c2d1ab14e255800e1fb3331ee7bc06cba4be"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.08435",
    "kind": "arxiv",
    "version": 2
  }
}