The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

• URL: http://arxiv.org/abs/2606.11918v1
• Date: Wed, 10 Jun 2026 10:50:06 GMT
• Title: The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
• Abstract summary: 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.
• Score: 65.67266333751569
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a knowledge deficit, relying on supervised fine-tuning (SFT) to ingest labeled spatial data from external vision sources or synthetic engines. In contrast, we argue that for many tasks, spatial reasoning capabilities are already present in pre-trained LRMs but require alignment through logical coherence under geometric 2D and 3D constraints. In this work, we propose a self-supervised reinforcement learning (RL) framework that targets the internal reasoning process without requiring ground-truth annotations. By formalizing the notion of consistency verifiers -- reward functions that check for geometric and semantic consistency under transformations -- we demonstrate that models can improve their spatial reasoning abilities. We use both image transformations, like flipping, and textual transformations, like swapping the order of objects in the question, and propose a new optimal transport-based RL strategy, OT-GRPO, which is a minimal-matching variant of group relative policy optimization tailored to pairwise verifiers. 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.

Related papers

• 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)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning [18.3204772691015]
  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.
  arXiv  Detail & Related papers  (2026-04-23T01:19:37Z)
• S-GRPO: Unified Post-Training for Large Vision-Language Models [11.901218794806796]
  We propose Supervised Group Relative Policy Optimization (S-GRPO) for adapting Large Vision-Language Models (LVLMs)<n>S-GRPO integrates the guidance of imitation learning into the multi-trajectory exploration of preference optimization.<n>It gracefully bridges the gap between Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)
  arXiv  Detail & Related papers  (2026-04-17T08:39:07Z)
• Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration [56.074760766965085]
  PRISM achieves a dynamics-aware framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.<n>Our findings suggest that disentangling data based on internal optimization regimes is crucial for scalable and robust agent alignment.
  arXiv  Detail & Related papers  (2026-01-12T05:43:20Z)
• From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization [62.07990937720985]
  Dimension-level Reward Model (DRM) is a new supervision framework for Large Language Models.<n>DRM evaluates the quality of a reasoning process along three fundamental, complementary, and interpretable dimensions.<n> Experimental results show that DRM provides effective supervision signals, guides the optimization of LLMs and enhances their reasoning ability.
  arXiv  Detail & Related papers  (2025-10-13T14:29:15Z)
• RACE-Align: Retrieval-Augmented and Chain-of-Thought Enhanced Preference Alignment for Large Language Models [11.107932406541865]
  This paper introduces RACE-Align, a novel framework designed to address the limitations of traditional preference alignment methods.<n> RACE-Align systematically constructs a binary preference dataset incorporating external knowledge support and explicit Chain-of-Thought (CoT) reasoning.<n> Experimental validation in Traditional Chinese Medicine (TCM) using Qwen3-1.7B as the base model demonstrates that RACE-Align significantly outperforms the original base model.
  arXiv  Detail & Related papers  (2025-06-03T10:36:38Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)

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.