Pith Number

pith:PPVKZDEH

pith:2026:PPVKZDEHDDS4UEBGUQD3IP2TPF

not attested not anchored not stored refs resolved

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Huazheng Wang, Jiayu Chang, Jishen Zhao, Nan Wang, Qingyun Wu, Yaolun Zhang, Yiran Wu, Yizhao Chen, Yujie Zhao

MetaAgent-X jointly trains the designer and executors of automatic multi-agent systems using end-to-end reinforcement learning.

arxiv:2605.14212 v1 · 2026-05-14 · 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{PPVKZDEHDDS4UEBGUQD3IP2TPF}

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

MetaAgent-X consistently outperforms existing automatic MAS baselines, achieving up to 21.7% gains. ... These results establish end-to-end trainable automatic MAS as a practical paradigm for building self-designing and self-executing agentic models.

C2weakest assumption

That Executor Designer Hierarchical Rollout and Stagewise Co-evolution provide stable joint optimization and accurate credit assignment across designer and executor trajectories without introducing new instabilities or biases that would prevent both components from improving.

C3one line summary

MetaAgent-X uses end-to-end RL to jointly optimize automatic multi-agent system design and execution, outperforming baselines by up to 21.7% through hierarchical rollouts and stagewise co-evolution.

References

52 extracted · 52 resolved · 0 Pith anchors

[1] Yujie Zhao, Hejia Zhang, Hanxian Huang, Zhongming Yu, and Jishen Zhao 2024

[2] 14 Figure 4: Sensitivity analysis on the stage length for designer–executor alternation

[3] Delivery formatting.Inter-agent messages must be strictly enclosed within <delivery>...</delivery> tags. This constraint serves a dual purpose: it establishes a structured, easily parsable communicati 2025

[4] Compute total number of ways to choose 4 numbers from 10:C(10,4)

[5] ComputeP(grand prize): number of ways to match all 4 numbers

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.919082Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7beaac8c8718e5ca1026a407b43f53795a72a8ee1a859b555d1376ab95508428

Aliases

arxiv: 2605.14212 · arxiv_version: 2605.14212v1 · doi: 10.48550/arxiv.2605.14212 · pith_short_12: PPVKZDEHDDS4 · pith_short_16: PPVKZDEHDDS4UEBG · pith_short_8: PPVKZDEH

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/PPVKZDEHDDS4UEBGUQD3IP2TPF \
  | 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: 7beaac8c8718e5ca1026a407b43f53795a72a8ee1a859b555d1376ab95508428

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "90b5dd0ee5f8c0671ad18c3c6869262239d1d5d063f971c2ea82535446863831",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T00:11:27Z",
    "title_canon_sha256": "2a3ceed12129c862013a513d84303942bd8ca228ef545f36479cf01b494d748f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14212",
    "kind": "arxiv",
    "version": 1
  }
}