Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

• URL: http://arxiv.org/abs/2608.01314v1
• Date: Sun, 02 Aug 2026 15:31:31 GMT
• Title: Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning
• Abstract summary: Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks.<n>As reasoning sequences lengthen, models may gradually rely less on visual evidence and more on accumulated textual context, leading to visual forgetting.<n>We propose Remember-R1, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory.
• Score: 50.56518447675037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthen, models may gradually rely less on visual evidence and more on accumulated textual context, leading to visual forgetting. Existing approaches do not directly constrain how visual evidence is used and maintained along the original reasoning trajectory, leaving long-context visual forgetting insufficiently addressed. To address this issue, we propose Remember-R1, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory. Specifically, Remember-R1 introduces rewards that encourage broader coverage of matched visual keywords, stronger persistence of visual dependence in later reasoning steps, and greater focus on question-relevant image regions. Experiments across multiple model scales and diverse multimodal benchmarks demonstrate that Remember-R1 consistently improves reasoning performance. Additional analyses further show that it slows the decline of visual attention during generation, supporting its effectiveness in mitigating long-context visual forgetting.

Related papers

• VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning [15.03674139835036]
  We propose VisionPulse, a step-wise visual token pruning framework during reasoning.<n>By enforcing visual sparsity during reasoning, VisionPulse filters redundant visual context while preserving relevant visual evidence, shortening reasoning traces naturally.
  arXiv  Detail & Related papers  (2026-05-29T15:51:12Z)
• Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention [41.546578522790114]
  Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models.<n>We propose Faithful-MR1, a training framework that anchors and reinforces visual attention to address both halves of faithful multimodal reasoning.
  arXiv  Detail & Related papers  (2026-05-21T07:10:18Z)
• IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning [15.580070614790776]
  Multimodal large language models via reinforcement learning have demonstrated remarkable capabilities in complex visual reasoning tasks.<n>Current methods pre-encode high-dimensional visual scenes into discrete textual proxies to facilitate downstream reasoning.<n>We introduce dynamic visual re-alignment that rectifies reasoning trajectories to guide optimization.
  arXiv  Detail & Related papers  (2026-05-18T09:53:08Z)
• Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification [55.357038267439684]
  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.
  arXiv  Detail & Related papers  (2026-03-27T12:22:13Z)
• VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models [21.438802784706994]
  We propose VisRef, a visually grounded test-time scaling framework.<n>Our key idea is to actively guide the reasoning process by re-injecting a coreset of visual tokens.<n>Under fixed test-time compute budgets, VisRef consistently outperforms existing test-time scaling approaches by up to 6.4%.
  arXiv  Detail & Related papers  (2026-02-27T11:48:19Z)
• Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning [50.62037276161025]
  Vision-language models (VLMs) aim to reason by jointly leveraging visual and textual modalities.<n>Key obstacle is that visual inputs are typically provided only once at the start of generation.<n>We propose emphSaliency-Aware Principle (SAP) selection.
  arXiv  Detail & Related papers  (2026-02-18T18:49:56Z)
• 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)
• Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
  Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
  arXiv  Detail & Related papers  (2025-05-26T17:51:47Z)
• Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models [62.698520962933195]
  Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning.<n>We propose a novel training-free context pruning method that selectively removes less critical textual information.
  arXiv  Detail & Related papers  (2024-10-25T17:59:09Z)

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.