Pith Number

pith:6JJ6BLBR

pith:2026:6JJ6BLBROSC5IO6TDA65HDTFV7

not attested not anchored not stored refs resolved

NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

Haoran Lu, Luyang Fang, Ping Ma, Wenxuan Zhong

Multi-agent language systems modeled as neural networks allow reinforcement learning to induce specialization and coordination among role-free agents.

arxiv:2605.16757 v1 · 2026-05-16 · cs.AI · cs.MA · stat.ME · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6JJ6BLBROSC5IO6TDA65HDTFV7}

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

Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems.

C2weakest assumption

That reinforcement learning training on the network topology can reliably induce effective specialization, communication protocols, and coordination among role-free agents without additional hand-designed constraints or semantic role assignments.

C3one line summary

NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.

References

65 extracted · 65 resolved · 7 Pith anchors

[1] Machine Learning , volume = 1992

[2] Parameter-Efficient Transfer Learning for 2019

[3] and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , booktitle =

[4] Learning Decentralized

[5] Yang, An and Li, Anfeng and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and Zheng, Bo and others , journal =

Receipt and verification

First computed	2026-05-20T00:03:20.176264Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625

Aliases

arxiv: 2605.16757 · arxiv_version: 2605.16757v1 · doi: 10.48550/arxiv.2605.16757 · pith_short_12: 6JJ6BLBROSC5 · pith_short_16: 6JJ6BLBROSC5IO6T · pith_short_8: 6JJ6BLBR

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/6JJ6BLBROSC5IO6TDA65HDTFV7 \
  | 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: f253e0ac317485d43bd3183dd38e65afc355b66926e127967d552a779e505625

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2f16af74cac9eb2e36dde6092b851db144c9ef1187308552b9d95f87a59ba1fc",
    "cross_cats_sorted": [
      "cs.MA",
      "stat.ME",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-16T02:11:34Z",
    "title_canon_sha256": "903b34c92712de8a7e3bd374f31b1280d3f4d883a03afece7c5d5cb021d05c77"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16757",
    "kind": "arxiv",
    "version": 1
  }
}