SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning

• URL: http://arxiv.org/abs/2604.21190v2
• Date: Tue, 28 Apr 2026 07:02:32 GMT
• Title: SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
• Abstract summary: spatial reasoning requires flexibly coordinating different strategies depending on the input.<n>Most existing approaches rely on a single reasoning pipeline that implicitly learns a fixed spatial prior.<n>We introduce SpatiO, a heterogeneous multi-agent framework for spatial reasoning that coordinates multiple vision-language specialists with complementary inductive biases.
• Score: 18.3204772691015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding visual scenes requires not only recognizing objects but also reasoning about their spatial relationships. Unlike general vision-language tasks, spatial reasoning requires integrating multiple inductive biases, such as 2D appearance cues, depth signals, and geometric constraints, whose reliability varies across contexts. This suggests that effective spatial reasoning requires \emph{spatial adaptability}: the ability to flexibly coordinate different reasoning strategies depending on the input. However, most existing approaches rely on a single reasoning pipeline that implicitly learns a fixed spatial prior, limiting their ability to adapt under distribution changes. Multi-agent systems offer a promising alternative by aggregating diverse reasoning trajectories, but prior attempts in spatial reasoning primarily employ homogeneous agents, restricting the diversity of inductive biases they can leverage. In this work, we introduce SpatiO, a heterogeneous multi-agent framework for spatial reasoning that coordinates multiple vision-language specialists with complementary inductive biases. To enable effective collaboration, we propose Test-Time Orchestration (TTO), an optimization mechanism that dynamically evaluates and reweights agents based on their observed reliability during inference, without modifying model parameters. Extensive experiments on diverse spatial reasoning benchmarks, including 3DSRBench, STVQA-7k, CV-Bench, and Omni3D-Bench, demonstrate that SpatiO consistently improves spatial reasoning performance over both closed-source and open-source baselines.

Related papers

• Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding [45.606064707494774]
  Mixture-of-Thought-Tokens (Motto) is a new free-form multimodal grounding method.<n>Motto bridges the perception-reasoning gap, enabling MLLMs to empower diverse, arbitrary grounding queries.<n>Extensive experiments demonstrate that Motto achieves state-of-the-art performance across diverse free-form grounding tasks.
  arXiv  Detail & Related papers  (2026-07-27T13:24:35Z)
• SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video [88.79625979053873]
  We propose a novel framework, SpaceEra, for pre-trained vision-language models (VLMs)<n>We extend the original framework into a comprehensive system, termed SpaceEra++, which spans data construction, model design, training optimization, and prompting inference.<n>In addition, to enhance spatial reasoning, we develop SpaceAlign, which enforces pairwise object constraints by jointly exploiting absolute coordinates and relative spatial relations.
  arXiv  Detail & Related papers  (2026-07-02T06:56:29Z)
• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency [53.28076739140119]
  We propose a framework that enforces logical consistency in Vision-Language Models (VLMs) through geometric and linguistic duality operations.<n>SAGE is model-agnostic, data-efficient compared to prior GRPO methods, and can be applied as a lightweight post-training stage to any existing VLM.<n> Experiments on video and spatial reasoning benchmarks demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-05-18T10:05:21Z)
• SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning [67.67774742200626]
  spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, is a core challenge for large language models.<n>We propose a unified multimodal generation framework that integrates textual reasoning with visual imagination.<n>Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation.
  arXiv  Detail & Related papers  (2026-04-19T11:21:59Z)
• GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy [31.32050433924969]
  Robust local feature detection and description are foundational tasks in computer vision.<n>Existing methods rely on single appearance cues for modeling, leading to unstable keypoints and insufficient descriptor discriminability.<n>We propose a multi-cue guided local feature learning framework that leverages semantic and geometric cues to enhance detection robustness and descriptor discriminability.
  arXiv  Detail & Related papers  (2026-04-07T02:57:26Z)
• Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network [31.003374497881968]
  Grassmannian manifold offers a powerful carrier for geometric representation learning.<n>We propose a topology-driven multi-subspace fusion framework that enables adaptive subspace collaboration on the Grassmannian.<n>Our work advances geometric deep learning and adapts the proven multi-channel interaction philosophy of Euclidean networks to non-Euclidean domains.
  arXiv  Detail & Related papers  (2025-11-09T10:33:13Z)
• Towards Inference-time Scaling for Continuous Space Reasoning [55.40260529506702]
  Inference-time scaling has proven effective for text-based reasoning in large language models.<n>This paper investigates whether such established techniques can be successfully adapted to reasoning in the continuous space.<n>We demonstrate the feasibility of generating diverse reasoning paths through dropout-based sampling.
  arXiv  Detail & Related papers  (2025-10-14T05:53:41Z)
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack [51.16384207202798]
  Vision-language pre-training models are vulnerable to multimodal adversarial examples (AEs) Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process. We propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity.
  arXiv  Detail & Related papers  (2024-11-04T23:07:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.