ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs

• URL: http://arxiv.org/abs/2605.25524v1
• Date: Mon, 25 May 2026 07:27:28 GMT
• Title: ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
• Abstract summary: We propose ProSR, a process-shaping optimization framework for spatial reasoning.<n>ProSR extends the optimization objective from single answer correctness to two process-level dimensions: visual dependence and trajectory stability.<n> Experiments show that ProSR improves answer accuracy while generating reasoning trajectories that are more stable and more dependent on visual evidence.
• Score: 37.068201407788884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the reasoning process, and therefore struggle to ensure genuine visual dependence and stable reasoning trajectories. In this paper, we construct a high-quality CoT dataset covering diverse spatial phenomena and diagnose the model's reasoning process, revealing two typical types of process degradation during reinforcement learning optimization: Spurious Grounding, which bypasses visual evidence, and Tail Instability, where uncertainty abnormally rises in the later stage of reasoning. To address these issues, we propose ProSR, a process-shaping optimization framework for spatial reasoning. Through a Counterfactual Invariance Penalty and a Tail Drift Penalty, ProSR extends the optimization objective from single answer correctness to two process-level dimensions: visual dependence and trajectory stability. Experiments on multiple complex and out-of-distribution spatial reasoning benchmarks show that ProSR improves answer accuracy while generating reasoning trajectories that are more stable and more dependent on visual evidence.

Related papers

• Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence [70.8951332710039]
  Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks.<n>However, their open-ended reasoning process is prone to decision errors and error accumulation, leading to instability in answer quality.<n>We propose an advantage-guided gating framework that dynamically intervenes in and corrects deviations during the reasoning process.
  arXiv  Detail & Related papers  (2026-08-08T07:46:04Z)
• Invariant Reasoning Directions in Latent Trajectories of Language Models [23.0736392766448]
  We show that latent reasoning trajectories contain stable invariant directions mixed with unstable instance-specific variation.<n>We introduce TILR, a training-free intervention framework for identifying and manipulating stable reasoning directions in latent space.<n>We find that TILR improves answer consistency under paraphrase by 10% and reduces latent trajectory variance by up to $50%$ while preserving reasoning accuracy.
  arXiv  Detail & Related papers  (2026-06-28T02:59:08Z)
• Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models [30.607422839762553]
  Bidirectional Manifold Consistency (BMC) is a training-free, unsupervised metric.<n>BMC serves as a robust discriminator of solution validity without ground truth answer.<n>Our results establish intrinsic geometric stability as a robust indicator of correctness for dLLMs.
  arXiv  Detail & Related papers  (2026-04-17T10:17:16Z)
• SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning [12.51459553492698]
  Self-Verification and Self-Rectification (SVSR) is a unified framework that integrates self-verification and self-rectification into the model's reasoning pipeline.<n>SVSR substantially improves robustness and reliability in complex visual understanding and multimodal reasoning tasks.
  arXiv  Detail & Related papers  (2026-04-11T14:25:17Z)
• Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability [32.78289130870447]
  TRACED is a framework that assesses reasoning quality through theoretically grounded geometric kinematics.<n>We reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns.
  arXiv  Detail & Related papers  (2026-03-11T03:58:43Z)
• Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment [97.55382322103986]
  Hit-RAG is a multi-stage preference alignment framework designed to resolve cognitive bottlenecks.<n>Our approach systematically refines the utilization of external evidence via three distinct stages.
  arXiv  Detail & Related papers  (2026-03-07T04:05:27Z)
• Learning Structured Reasoning via Tractable Trajectory Control [99.75278337895024]
  Ctrl-R is a framework for learning structured reasoning via tractable trajectory control.<n>We show that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns.
  arXiv  Detail & Related papers  (2026-03-02T09:18:19Z)
• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• On the Plasticity and Stability for Post-Training Large Language Models [54.757672540381236]
  We identify a root cause as the conflict between plasticity and stability gradients.<n>We propose Probabilistic Conflict Resolution (PCR), a framework that models gradients as random variables.<n>PCR significantly smooths the training trajectory and achieves superior performance in various reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-06T07:31:26Z)
• Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning [16.244366307890832]
  We propose textbfDeepLatent Reasoning (DLR), a latent-space bidirectional contrastive reinforcement learning framework.<n>This framework shifts the trial-and-error cost from expensive token-level full sequence generation to the continuous latent manifold.<n> Experiments demonstrate that DLR achieves more stable training convergence, supports longer-horizon reasoning chains, and facilitates the sustainable accumulation of reasoning capabilities.
  arXiv  Detail & Related papers  (2026-01-24T03:18:22Z)
• CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation [6.356820150960838]
  We introduce two complementary approaches inspired by test-time scaling to stabilize vision-language models.<n>CASHEW is an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces.<n>CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence.
  arXiv  Detail & Related papers  (2026-01-12T21:24:45Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)

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.