pith. sign in
Pith Number

pith:AM5XLQQY

pith:2026:AM5XLQQYV7ROFBPT4PRZSUIGDT
not attested not anchored not stored refs resolved

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems

Hongji Pu, Liang Zhao, Xinyuan Song

SkillOps maintains LLM skill libraries via Skill Contracts and ecosystem graphs, raising ALFWorld task success to 79.5% as a standalone agent and improving retrieval baselines by up to 2.9 points with near-zero library-time LLM cost.

arxiv:2605.13716 v1 · 2026-05-13 · cs.SE · cs.MA

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AM5XLQQYV7ROFBPT4PRZSUIGDT}

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 ALFWorld, SkillOps achieves 79.5 percent task success as a standalone agent, outperforming the strongest baseline by 8.8 percentage points with no additional task-time large language model calls.

C2weakest assumption

That rule-based diagnosis across the four health dimensions (utility, compatibility, risk, validation) can reliably detect and repair library-level defects without task-specific LLM calls or human oversight.

C3one line summary

SkillOps maintains LLM skill libraries via Skill Contracts and ecosystem graphs, raising ALFWorld task success to 79.5% as a standalone agent and improving retrieval baselines by up to 2.9 points with near-zero library-time LLM cost.

References

52 extracted · 52 resolved · 16 Pith anchors

[1] Fundamenta Mathematicae , volume =
[2] SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks · arXiv:2602.12670
[3] Alessandro Berti and Sebastiaan van Zelst and Wil M. P. van der Aalst , title =. 2019 , eprint = 2019
[4] 2026 , eprint = 2026
[5] 2025 , eprint = 2025
Receipt and verification
First computed 2026-05-18T02:44:16.704665Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

033b75c218afe2e285f3e3e39951061cd8d853943ae3f86d6256db09c9d0af65

Aliases

arxiv: 2605.13716 · arxiv_version: 2605.13716v1 · doi: 10.48550/arxiv.2605.13716 · pith_short_12: AM5XLQQYV7RO · pith_short_16: AM5XLQQYV7ROFBPT · pith_short_8: AM5XLQQY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AM5XLQQYV7ROFBPT4PRZSUIGDT \
  | 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: 033b75c218afe2e285f3e3e39951061cd8d853943ae3f86d6256db09c9d0af65
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "dee088cbdfcb1c39f37c813f25f4828eecc3179bf53ade38ee5656e9bc1b8ad6",
    "cross_cats_sorted": [
      "cs.MA"
    ],
    "license": "http://creativecommons.org/publicdomain/zero/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-13T16:02:25Z",
    "title_canon_sha256": "67ae17563200187eebb2a3646aea99b7bda6549df51e411205482f583c928f22"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13716",
    "kind": "arxiv",
    "version": 1
  }
}