arXiv AI August 3, 2026 By Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin, Abdullah Ibne Hanif Arean, Juena Ahmed Noshin

Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models

Read the original on arXiv AI →

arXiv:2603. 06828v2 Announce Type: replace-cross Abstract: We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 6

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.

By Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott

llms multimodal safety

arXiv AI

Jun 16

Thinking with Visual Grounding

arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.

By Junkai Zhang, Yihe Deng, Kai-Wei Chang, Wei Wang

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

Jul 16

Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.

By Jae Joong Lee

llms benchmarks

arXiv AI

Jul 7

Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding

arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.

By Animesh Tripathy, Aswanth Krishnan

llms multimodal

arXiv AI

Jun 17

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models

arXiv:2606. 17389v1 Announce Type: cross Abstract: Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical.

By Logan Mann, Yi Xia, Ajit Saravanan, Ishan Dave, Saadullah Ismail, Shikhar Shiromani, Emily Huang, Ruizhe Li, Kevin Zhu

llms agents multimodal

arXiv AI

Jul 21

Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models

arXiv:2607. 17786v1 Announce Type: cross Abstract: Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation?

By Tuan Duong Trinh, Naveed Akhtar, Basim Azam

multimodal safety

Related stories

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

Thinking with Visual Grounding

Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models

Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models