Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs

• URL: http://arxiv.org/abs/2608.04759v1
• Date: Wed, 05 Aug 2026 12:26:23 GMT
• Title: Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs
• Abstract summary: We propose a modular and training-free framework for spatial reasoning verification and correction.<n>The framework associates atomic spatial evidence extracted from Chain-of-Thought reasoning with visual entities, spatial relations, source steps, and visual evidence.<n>Across 15 model-dataset settings, our method achieves an average accuracy of 68.94%, outperforming the compared baselines by 8.55 percentage points.
• Score: 11.359645786865359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inconsistent with the input image, allowing errors to propagate through the reasoning chain and affect the final answer. Existing methods mainly improve spatial reasoning through training or additional spatial information, without considering whether the reasoning process itself is faithful to the model input. Our study shows that unfaithful reasoning chains significantly reduce final-answer accuracy. To address this issue, we propose a modular and training-free framework for spatial reasoning verification and correction. The framework constructs a Spatial Evidence Graph (SEG), which associates atomic spatial evidence extracted from Chain-of-Thought reasoning with visual entities, spatial relations, source steps, and visual evidence. Spatial Evidence Reliability Assessment (SERA) evaluates the reliability of visual evidence based on object existence, localization, and geometric measurements. The framework then identifies the earliest spatial evidence unit contradicted by reliable visual evidence and guides the original MLLM to revise the subsequent reasoning and final answer. Across 15 model-dataset settings, our method achieves an average accuracy of 68.94%, outperforming the compared baselines by 8.55 percentage points on average. Our code will be open-sourced.

Related papers

• Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes [37.743333035442426]
  This paper introduces AD2-Bench, which decomposes reasoning into a structured Chain of Evidence (CoE)<n>Building on this perspective, the authors identify two primary causes of reasoning failure: Spatial Ambiguity and Semantic Uncertainty.<n>They then propose Evidence-grounded Visual Reasoning (EGVOR), which replaces implicit reasoning with the explicit generation of Evidence Atoms.
  arXiv  Detail & Related papers  (2026-08-11T14:23:07Z)
• Latent Fact-Checking: Detecting Misinformation through Activation Engineering [1.3299946892361476]
  We introduce a misinformation detection framework grounded in activation engineering.<n>Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements.<n>We evaluate the method across 11 models on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors.
  arXiv  Detail & Related papers  (2026-08-05T18:00:14Z)
• RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought [50.36951914894845]
  Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments.<n>Current vision-language models rely on text-only or coordinate-augmented chain-of-thought.<n>We propose Pinned Chain-of-Thought, a structured reasoning paradigm that pins every reasoning step to visual evidence.
  arXiv  Detail & Related papers  (2026-06-14T11:30:42Z)
• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models [154.39583176906893]
  Large language models (MLs) have advanced understanding, they remain highly prone to hallucinations in scenes.<n>We argue this stems from a failure intemporal monitoring, the ability to persistently track object dynamic identities, states, and relations over time.<n>Existing benchmarks obscure this deficit relying on single final-answer queries that can often be resolved via local visual cues or statistical priors.
  arXiv  Detail & Related papers  (2026-05-09T14:32:36Z)
• Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning [11.05919811646786]
  We propose RIS (Retrieve, Integrate, and Synthesize), a spatial-semantic grounded framework that develops latent reasoning as a compatible extension of pretrained MLLM computation.<n>RIS anchors latent tokens to both spatial and semantic evidence, enforces their causal role through a progressive attention bottleneck, and introduces short language transition tokens to bridge synthesized latent states back to vocabulary-aligned decoding.
  arXiv  Detail & Related papers  (2026-05-08T01:33:58Z)
• See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs [24.90876091319589]
  We present an iterative, training-free, plug-and-play framework for visually-grounded multimodal reasoning.<n>Our key idea is to supervise each reasoning step at test time with visual evidence.<n>Our method achieves 16.5%-29.5% improvements on TreeBench and 13.7% RH-AUC gains on RH-Bench.
  arXiv  Detail & Related papers  (2026-02-25T02:13:59Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)
• 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)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)

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.