Explainable and Resource-Efficient Spatial Reasoning in Multimodal LLMs for Decision-Critical Applications

• URL: http://arxiv.org/abs/2607.27145v1
• Date: Wed, 29 Jul 2026 17:20:56 GMT
• Title: Explainable and Resource-Efficient Spatial Reasoning in Multimodal LLMs for Decision-Critical Applications
• Abstract summary: Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitoring.<n>MLLMs demonstrate strong reasoning but often struggle with fine-grained spatial understanding and object hallucination.<n>We propose ByDeWay-V2, which integrates explicit spatial context alongside depth cues.
• Score: 7.911287368927542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitoring, the opacity of their spatial judgments limits operator trust and auditability. MLLMs demonstrate strong reasoning but often struggle with fine-grained spatial understanding and object hallucination. Prior work, ByDeWay, introduced Layered-Depth-Based Prompting (LDP), a training-free framework that mitigates hallucinations by structuring prompts using monocular depth estimation. However, coarse depth layering falls short in resolving object-to-object spatial relationships within the same geometric plane, such as projective ("left of", "above") and topological ("inside", "touching") relations. We propose ByDeWay-V2, which integrates explicit spatial relational context alongside depth cues, expressed as human-readable predicates that serve as auditable evidence for downstream decision support. Using an open-vocabulary object detector (YOLO-World-L), our framework computes pairwise geometric relations between detected objects and injects them as structured spatial predicates into the MLLM prompt, bridging 3D scene depth and 2D spatial semantics without any training. We evaluate ByDeWay-V2 on the Visual Spatial Reasoning (VSR) and BLINK benchmarks across multiple MLLMs, with hallucination grounding assessed via POPE. On the BLINK spatial subset, ByDeWay-V2 achieves a 46 percent relative F1 improvement over LDP for Qwen2.5-VL, and recovers BLIP-Base's spatial reasoning on VSR from near-random performance to a competitive F1 of 0.53. Our lightest configuration operates under a strict 40-token context budget on CPU, showing the framework's suitability for resource-constrained, real-time decision-support settings.

Related papers

• 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)
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning [99.49739831030388]
  We study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning.<n>We propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface.
  arXiv  Detail & Related papers  (2026-06-11T17:59:36Z)
• EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs [36.84953281346447]
  EgoMind is a Chainof-Thought framework that enables geometry-free spatial reasoning through RolePlay Caption.<n>With only 5K samples and 20K RL samples, EgoMind achieves effectiveness in MLLMBenchs, SITEBench, and SPBench.
  arXiv  Detail & Related papers  (2026-04-01T15:28:13Z)
• AgentVLN: Towards Agentic Vision-and-Language Navigation [78.739525400071]
  Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments.<n>In this paper, we propose AgentVLN, a novel and efficient embodied navigation framework that can be deployed on edge computing platforms.
  arXiv  Detail & Related papers  (2026-03-18T12:43:47Z)
• Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration [16.651645602449577]
  Vision-and-Language Navigation (VLN) agents leveraging Large Language Models (LLMs) excel in generalization but suffer from insufficient spatial perception.<n>We present Spatial-VLN, a perception-guided exploration framework designed to overcome these challenges.
  arXiv  Detail & Related papers  (2026-01-19T06:53:02Z)
• SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion [23.86761713752287]
  Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks.<n>Most MLLMs suffer from limited spatial reasoning ability to interpret and infer spatial arrangements in three-dimensional space.<n>We propose a novel vision encoder based on hierarchical fusion of geometry and semantics features, generating spatial-aware visual embedding.
  arXiv  Detail & Related papers  (2025-11-21T15:24:33Z)
• SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards [37.39035418889281]
  We introduce SpatialThinker, a 3D-aware MLLM trained with RL to integrate structured spatial grounding with multi-step reasoning.<n>The model simulates human-like spatial perception by constructing a scene graph of task-relevant objects and spatial relations, and reasoning towards an answer via dense spatial rewards.
  arXiv  Detail & Related papers  (2025-11-10T18:52:47Z)
• FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning [62.11389260206383]
  textscFineRS is a two-stage MLLM-based reinforcement learning framework for segmenting extremely small objects.<n>We present textscFineRS-4k, a new dataset for evaluating MLLMs on attribute-level reasoning and pixel-level segmentation on subtle, small-scale targets.
  arXiv  Detail & Related papers  (2025-10-24T10:14:17Z)
• A Multimodal Depth-Aware Method For Embodied Reference Understanding [56.30142869506262]
  Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues.<n>We propose a novel ERU framework that jointly leverages data augmentation, depth-map modality, and a depth-aware decision module.
  arXiv  Detail & Related papers  (2025-10-09T14:32:21Z)
• Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding [8.202861909913791]
  We present a benchmark for object-centric spatial reasoning in foundation models.<n>We find a stable trade-off: detectors such as GroundingDINO and OWLv2 deliver precise boxes with limited relational reasoning.<n>Our study highlights the gap between localization and true spatial understanding, and pointing toward the need for spatially-aware foundation models in the community.
  arXiv  Detail & Related papers  (2025-09-26T06:06:19Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)

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.