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.
Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds
The paper investigates how visual presentation affects vision‑language models (VLMs) on the SPaRC spatial planning benchmark. By adding lightweight input‑side scaffolds that keep the visual modality but make spatial structure clearer, the authors achieve up to a 34.0‑percentage‑point accuracy boost across multiple VLMs, and an additional 4.6 points when combined with GRPO training. Analyses reveal that these improvements stem mainly from reduced grounding errors, while rule‑based reasoning remains difficult, highlighting visual presentation as a key determinant of whether VLM benchmarks test grounded perception, downstream reasoning, or both.
Related stories
arXiv AI
Jul 14
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
arXiv:2607. 11436v1 Announce Type: new Abstract: Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning.
arXiv AI
Jul 7
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.
arXiv AI
Sep 2
ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
arXiv:2505.13180v3 Announce Type: replace Abstract: Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works ex...
arXiv AI
Oct 1
SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models
arXiv:2609.38716v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weaknes...
arXiv Computer Vision
Oct 8
Flow-of-Thought: A Framework for Visual Reasoning
arXiv:2610.09746v1 Announce Type: new Abstract: Mental imagery, ``seeing with the mind's eye'' is an essential aspect of human cognition. Despite rapid progress Large Language Models (LLMs) and Visio...
arXiv AI
4d ago
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
CoWorld Reasoner is an agentic framework that leverages a Video World Model (VWM) as a unified visual reasoning engine for Vision‑Language Models (VLMs). It exposes multiple visual operations through tools and skills, allowing the VLM to decide when to imagine, select an operation, generate visual content, and interpret the resulting evidence. The framework includes a VLM‑VWM Harness Co‑Evolution mechanism that jointly refines tools, skills, and execution code based on feedback, while keeping model weights fixed. Across seven benchmarks covering spatial, temporal, causal, and perceptual reasoning, CoWorld Reasoner outperforms direct VLM reasoning and improves accuracy on all benchmarks, achieving notable gains on MMSI and ERQA.
arXiv Machine Learning
Aug 21
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
arXiv:2608. 19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage.
arXiv AI
Jun 12
Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
arXiv:2606. 12830v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction.
arXiv Computer Vision
4d ago
Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs
The paper introduces Perception and Reasoning Attribution (PARA), a method that quantifies how much of a vision‑language model’s errors can be fixed by better perception versus stronger reasoning. PARA reveals that reinforcement learning (RL) benefits more from improving reasoning than perception, and motivates a new group‑relative attention distillation objective called GRAD. GRAD directly guides weaker rollouts toward the visual attention patterns of the best rollouts, consistently boosting performance across multiple model scales and benchmarks.
arXiv AI
Aug 5
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
arXiv:2607. 27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning.
arXiv AI
Sep 7
MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
MultihopSpatial is a new benchmark for Vision‑Language Models that focuses on multi‑hop, compositional spatial reasoning with queries ranging from 1 to 3 hops across varied spatial perspectives. It introduces the Acc@50IoU metric, which jointly evaluates answer selection and precise bounding‑box prediction, and provides a large‑scale training corpus, MultihopSpatial‑Train, to improve spatial intelligence. Evaluation of 37 state‑of‑the‑art VLMs shows that compositional spatial reasoning remains a significant challenge, and reinforcement learning fine‑tuning on the corpus boosts both intrinsic spatial reasoning and downstream embodied manipulation performance.