Pith Number

pith:26HI5JTC

pith:2026:26HI5JTCZSCNBSUVPC6MD4G5XZ

not attested not anchored not stored refs pending

How Mobile World Model Guides GUI Agents?

Bo An, Heng Qu, Jian Luan, Jiaxing Li, Kun Huang, Pengzhi Gao, Weikai Xu, Wei Liu, Xiaolin Hu, Yuhan Chen, Yunren Feng, Yuxuan Liu, Zhizheng Jiang

World models improve mobile GUI agent performance as training supervision but show limited value in post-hoc self-reflection for overconfident agents.

arxiv:2605.10347 v2 · 2026-05-11 · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{26HI5JTCZSCNBSUVPC6MD4G5XZ}

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

world-model-generated trajectories can provide transferable interaction experience in the training process and improve agents' end-to-end task performance, although these data do not preserve the original distribution; for overconfident mobile agents with low action entropy, posterior self-reflection provides limited gains, suggesting that world models are more effective as prior perception or training supervision than as universal post-hoc verifiers.

C2weakest assumption

That the downstream evaluations on AITZ, AndroidControl, and AndroidWorld, together with the chosen agent strengths and entropy measures, isolate the contribution of the world models without confounding effects from data filtering choices or benchmark construction.

C3one line summary

Mobile world models in text, image, and code modalities reach state-of-the-art on their benchmarks and improve downstream GUI agent performance, with code best for in-distribution accuracy and text more robust for out-of-distribution use.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-25T02:01:22.921902Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d78e8ea662cc84d0ca9578bcc1f0ddbe42bed3c7778f4bcf39f62d27ea5c2ee3

Aliases

arxiv: 2605.10347 · arxiv_version: 2605.10347v2 · doi: 10.48550/arxiv.2605.10347 · pith_short_12: 26HI5JTCZSCN · pith_short_16: 26HI5JTCZSCNBSUV · pith_short_8: 26HI5JTC

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/26HI5JTCZSCNBSUVPC6MD4G5XZ \
  | 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: d78e8ea662cc84d0ca9578bcc1f0ddbe42bed3c7778f4bcf39f62d27ea5c2ee3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2f9dda26a762881c0544da5ce8f68c69067ceb15e3a83e61ca4ef98185f45e4e",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-11T10:49:31Z",
    "title_canon_sha256": "d5258255c7a409ed66fd43b173ae371c09d053c3ac3028f02a7c29c74b7a6606"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10347",
    "kind": "arxiv",
    "version": 2
  }
}