Pith Number

pith:F7OKRRH4

pith:2026:F7OKRRH4TKXYSJMWPJTZ2NYUKF

not attested not anchored not stored refs pending

MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?

Bin Liu, Lan-Zhe Guo, Lingyue Ge, Shi-Yu Tian, Weiming Wu, Wenbo Fu, Xiangwen Zhang, Yang Chen, Yu-Feng Li, Yulan Hu, Zhenyu Huang, Zi-Jian Cheng, Ziqiao Shang

Multimodal large language models face substantial challenges in multi-criteria route planning that combines map images with tabular data.

arxiv:2602.18600 v3 · 2026-02-20 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{F7OKRRH4TKXYSJMWPJTZ2NYUKF}

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

Extensive evaluations across 15 representative MLLMs reveal that current models face substantial challenges in multi-criteria multimodal reasoning. Notably, under conditions of limited visual perception, multimodal collaboration often underperforms compared to unimodal approaches.

C2weakest assumption

The constructed queries and four criteria (Time, Price, Comfort, Reliability) are assumed to form a faithful and sufficiently difficult proxy for real-world multi-criteria route planning that generalizes beyond the chosen 160 cities and 168 attractions.

C3one line summary

MapTab benchmark shows current MLLMs struggle with multi-criteria multimodal route planning and that combining vision and language frequently underperforms single-modality approaches.

Formal links

1 machine-checked theorem link

Cited by

1 paper in Pith

LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models

Receipt and verification

First computed	2026-05-22T01:03:58.680300Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2fdca8c4fc9aaf8925967a679d371451513b1101e3cac7c7d28ae45bac3a7cc2

Aliases

arxiv: 2602.18600 · arxiv_version: 2602.18600v3 · doi: 10.48550/arxiv.2602.18600 · pith_short_12: F7OKRRH4TKXY · pith_short_16: F7OKRRH4TKXYSJMW · pith_short_8: F7OKRRH4

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/F7OKRRH4TKXYSJMWPJTZ2NYUKF \
  | 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: 2fdca8c4fc9aaf8925967a679d371451513b1101e3cac7c7d28ae45bac3a7cc2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "604fd920c196bb9ec9df9bba21733ab23ef1417cbcc77a45ad2fba8b385cb1e6",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-20T20:22:18Z",
    "title_canon_sha256": "aead3dc36643a46d205a2afd44e2e750b4ade9ca6daf75815b2b545167ae6e4b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.18600",
    "kind": "arxiv",
    "version": 3
  }
}