Pith Number

pith:6QS3OIBM

pith:2026:6QS3OIBMID4YM746F42RZYUPGR

not attested not anchored not stored refs pending

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

Bingyang Zheng, Cheng Wang, Fengyang Li, Jingyi Chai, Linfeng Zhang, Rui Ye, Ruoxue Liao, Shuo Tang, Siheng Chen, Tingjia Miao, Wanxu Liu, Weinan E, Wenkai Jin, Xianghe Pang, Xinyu Zhu, Yanfeng Wang, Yaxin Du, Yuwen Du, Yuzhi Zhang, Yuzhu Cai, Zehao Bing, Zexi Liu, Zhaohan Ding

EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation.

arxiv:2604.17406 v3 · 2026-04-19 · 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{6QS3OIBMID4YM746F42RZYUPGR}

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

EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3% on Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience respectively, comprehensively outperforming the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%.

C2weakest assumption

That the described continuous self-evolution process produces genuine improvements in scientific reasoning and discovery capability rather than benchmark-specific optimizations or superficial gains.

C3one line summary

EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains.

Receipt and verification

First computed	2026-06-09T01:05:17.509458Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5

Aliases

arxiv: 2604.17406 · arxiv_version: 2604.17406v3 · doi: 10.48550/arxiv.2604.17406 · pith_short_12: 6QS3OIBMID4Y · pith_short_16: 6QS3OIBMID4YM746 · pith_short_8: 6QS3OIBM

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/6QS3OIBMID4YM746F42RZYUPGR \
  | 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: f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4ea9375219fde31525eaa7b9ba7235c33ccdda4ced060a0d76b766234db661aa",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-19T12:26:05Z",
    "title_canon_sha256": "f1fa16a77866ce189a142a3a36acde5c71251fdefe26346b88e28e37fed3c793"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.17406",
    "kind": "arxiv",
    "version": 3
  }
}