Pith Number

pith:LYBM63DI

pith:2026:LYBM63DI6ZAUOXS5X4LKH256ST

not attested not anchored not stored refs resolved

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering

Deyang Li, Enrui Hu, Fangchao Liu, Hongbo Wang, Jianjun Tao, Qi Ye, Ruifeng Shi, Shuo Cheng, Xinyu Zhang, Xuefeng Jin, Yangkai Ding, Zhangchun Zhao, Zhicheng Dou

Swarm Skills turns multi-agent coordination into portable, self-evolving assets without framework lock-in

arxiv:2605.10052 v2 · 2026-05-11 · cs.CL · 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{LYBM63DI6ZAUOXS5X4LKH256ST}

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

Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in.

C2weakest assumption

The self-evolution algorithm, driven by multi-dimensional scoring of Effectiveness, Utilization, and Freshness, can reliably distill and patch coordination strategies without human oversight or introducing degradation over repeated cycles.

C3one line summary

Swarm Skills is a portable multi-agent coordination specification with roles, workflows, bounds, and a self-evolution algorithm that distills trajectories using Effectiveness, Utilization, and Freshness scores for zero-adapter portability.

References

16 extracted · 16 resolved · 0 Pith anchors

[1] AgentVerse: Facilitating multi-agent collaboration and ex- ploring emergent behaviors 2024

[2] MetaGPT: Meta programming for a multi-agent collaborative framework 2024

[3] CAMEL: Communicative agents for “mind” exploration of large language model society 2023

[4] SAGE: Self-evolving agents with reflective and memory-augmented abilities 2025

[5] A dynamic LLM-powered agent network for task-oriented agent collaboration 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:42.306430Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5e02cf6c68f641475e5dbf16a3ebbe94c8e84978e5354b35a43cd0aa98aad8b6

Aliases

arxiv: 2605.10052 · arxiv_version: 2605.10052v2 · doi: 10.48550/arxiv.2605.10052 · pith_short_12: LYBM63DI6ZAU · pith_short_16: LYBM63DI6ZAUOXS5 · pith_short_8: LYBM63DI

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/LYBM63DI6ZAUOXS5X4LKH256ST \
  | 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: 5e02cf6c68f641475e5dbf16a3ebbe94c8e84978e5354b35a43cd0aa98aad8b6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "701cbe5343f36d78f07b5a5d60539967f9a667b6e7fd227d2f43551b6157bbba",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-11T06:26:58Z",
    "title_canon_sha256": "b1f6637af083a0589bd8577110326a6e89b0740a8ca6853e10bbc947cd4b2d2c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10052",
    "kind": "arxiv",
    "version": 2
  }
}