Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification

• URL: http://arxiv.org/abs/2603.26348v1
• Date: Fri, 27 Mar 2026 12:22:13 GMT
• Title: Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
• Abstract summary: Visual Re-Examination (VRE) is a self-evolving training framework that enables MLLMs to autonomously perform visual introspection during reasoning without additional visual inputs.<n>VRE consistently improves reasoning accuracy and perceptual reliability, while substantially reducing hallucinations, especially in long-chain settings.
• Score: 55.357038267439684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall back on textual priors, resulting in ungrounded reasoning and hallucinations. Interestingly, Based on attention analysis, we find that MLLMs have a latent capability for late-stage visual verification that is present but not consistently activated. Motivated by this observation, we propose Visual Re-Examination (VRE), a self-evolving training framework that enables MLLMs to autonomously perform visual introspection during reasoning without additional visual inputs. Rather than distilling visual capabilities from a stronger teacher, VRE promotes iterative self-improvement by leveraging the model itself to generate reflection traces, making visual information actionable through information gain. Extensive experiments across diverse multimodal benchmarks demonstrate that VRE consistently improves reasoning accuracy and perceptual reliability, while substantially reducing hallucinations, especially in long-chain settings. Code is available at https://github.com/Xiaobu-USTC/VRE.

Related papers

• Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training [82.17582358979884]
  Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>We propose VISTA, a vision-aware self-improvement training framework for enhancing the multimodal reasoning of MLLMs.
  arXiv  Detail & Related papers  (2026-05-12T10:44:35Z)
• Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time [9.870369982132678]
  Multimodal large language models (MLLMs) have revolutionized the landscape of AI.<n>These models often suffer from hallucinations, generating outputs that diverge from the provided perceptual inputs.<n>We propose Learning Inference-time Modality Enhancement (LIME) to bolster multimodal grounding.
  arXiv  Detail & Related papers  (2026-05-03T07:58:02Z)
• Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization [89.68681087743876]
  Multimodal Large Language Models (MLLMs) have incentivized models to think with images'' by actively invoking visual tools during multi-turn reasoning.<n>The common Reinforcement Learning practice of relying on outcome-based rewards ignores the fact that textual plausibility often masks executive failure.<n>We introduce Multimodal Agentic Policy Optimization (MAPO), bridging the gap between textual reasoning and visual actions generated by models within their Multimodal Chain-of-Thought.
  arXiv  Detail & Related papers  (2026-04-08T07:48:07Z)
• Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models [3.9189409002585553]
  Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs.<n>We show that dMLLMs tend to generate premature final answers without sufficiently grounding on visual inputs.<n>We propose Position and Step Penalty (PSP) and Visual Reasoning Guidance (VRG) to address these limitations.
  arXiv  Detail & Related papers  (2026-04-07T06:41:05Z)
• Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
  We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:28:07Z)
• Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs [60.93949629734977]
  We propose Visual Contrastive Self-Taught Reasoner (VC-STaR) to mitigate hallucinations in model-generated rationales.<n>We collect a diverse suite of VQA datasets, curate contrastive pairs according to multi-modal similarity, and generate rationales using VC-STaR.<n>Extensive experiments show that VC-STaR not only outperforms existing self-improving approaches but also surpasses models finetuned on the SoTA visual reasoning datasets.
  arXiv  Detail & Related papers  (2026-03-03T03:18:31Z)
• Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs [55.61018839017648]
  Chain-of-thought (CoT) reasoning has substantially improved multimodal large language models (MLLMs) on complex reasoning tasks.<n>Existing approaches largely rely on long textual reasoning trajectories and provide limited mechanisms for learning stable visual attention policies.<n>We propose SAYO, a visual reasoning model trained with a reinforcement learning framework that introduces a region-level visual attention-based reward.
  arXiv  Detail & Related papers  (2026-02-09T03:33:23Z)
• V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval [32.5242219186118]
  We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection.<n>V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification.
  arXiv  Detail & Related papers  (2026-02-05T18:59:21Z)
• Vision-aligned Latent Reasoning for Multi-modal Large Language Model [82.26044667101011]
  Vision-aligned Latent Reasoning (VaLR) is a framework that dynamically generates vision-aligned latent tokens before each Chain of Thought reasoning step.<n>VaLR is trained to preserve visual knowledge during reasoning by aligning intermediate embeddings of MLLM with those from vision encoders.
  arXiv  Detail & Related papers  (2026-02-04T12:04:02Z)
• MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning [20.14427952871989]
  We introduce MMRPT, a multimodal reinforcement pre-training framework that strengthens visual reasoning in MLLMs.<n>We are the first to incorporate reinforcement learning directly into the pre-training of large vision-language models.<n>Experiments show consistent zero-shot gains across diverse benchmarks and substantially improved robustness under supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-12-08T06:26:13Z)
• Look-Back: Implicit Visual Re-focusing in MLLM Reasoning [15.478700750705643]
  Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning.<n>Current methods typically address this by explicitly injecting visual information to guide the reasoning process.<n>We introduce Look-Back, an implicit approach designed to guide MLLMs to look back" at visual information in a self-directed manner during reasoning.
  arXiv  Detail & Related papers  (2025-07-02T14:59:35Z)
• Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward [77.34936657745578]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)

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.