Pith Number

pith:JFWDTT5N

pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N

not attested not anchored not stored refs pending

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Alina Geiger, Dominik Sobania, Federica Sarro, Jie M. Zhang, Jingzhi Gong, Lukas Twist, Ruizhen Gu, Shuo Han, Yazhuo Cao, Zhiwei Fei

SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.

arxiv:2604.09297 v2 · 2026-04-10 · cs.SE · 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{JFWDTT5N2R3SLTIJFAQK3P2B5N}

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

On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.

C2weakest assumption

That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics.

C3one line summary

SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.

Cited by

1 paper in Pith

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Receipt and verification

First computed	2026-05-20T00:03:10.907210Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e

Aliases

arxiv: 2604.09297 · arxiv_version: 2604.09297v2 · doi: 10.48550/arxiv.2604.09297 · pith_short_12: JFWDTT5N2R3S · pith_short_16: JFWDTT5N2R3SLTIJ · pith_short_8: JFWDTT5N

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/JFWDTT5N2R3SLTIJFAQK3P2B5N \
  | 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: 496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-04-10T13:08:01Z",
    "title_canon_sha256": "0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.09297",
    "kind": "arxiv",
    "version": 2
  }
}