Pith. sign in

REVIEW 4 cited by

Can Large Vision Language Models Read Maps Like a Human?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.14607 v1 pith:6LA4VCVC submitted 2025-03-18 cs.CV

classification cs.CV
keywords mapbenchlvlmsnavigationdatasetfindinglanguagemapspath
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we introduce MapBench-the first dataset specifically designed for human-readable, pixel-based map-based outdoor navigation, curated from complex path finding scenarios. MapBench comprises over 1600 pixel space map path finding problems from 100 diverse maps. In MapBench, LVLMs generate language-based navigation instructions given a map image and a query with beginning and end landmarks. For each map, MapBench provides Map Space Scene Graph (MSSG) as an indexing data structure to convert between natural language and evaluate LVLM-generated results. We demonstrate that MapBench significantly challenges state-of-the-art LVLMs both zero-shot prompting and a Chain-of-Thought (CoT) augmented reasoning framework that decomposes map navigation into sequential cognitive processes. Our evaluation of both open-source and closed-source LVLMs underscores the substantial difficulty posed by MapBench, revealing critical limitations in their spatial reasoning and structured decision-making capabilities. We release all the code and dataset in https://github.com/taco-group/MapBench.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.

  2. VLM@school -- Evaluation of AI image understanding on German middle school knowledge

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A new German middle school visual question-answering benchmark shows open-weight VLMs score below 45% overall, with especially weak results in music, math, and adversarial questions.

  3. SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

    cs.AI 2025-06 reject novelty 5.0 of 10

    SAFEFLOW wraps LLM/VLM agents in fine-grained information-flow control, verifier-gated trust adjustment, and transactional concurrency, and its authors report near-perfect safety on their own benchmark plus AgentHarm,...

  4. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

    cs.CV 2025-06 reject novelty 4.0 of 10

    Multimodal LLM accuracy can improve on visually degraded images, and a lightweight test-time tuning module that modulates input quality yields small accuracy gains on some benchmarks.

Pith tools