ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction

• URL: http://arxiv.org/abs/2605.11212v2
• Date: Wed, 13 May 2026 16:34:05 GMT
• Title: ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
• Abstract summary: ReVision is used to train multimodal language models on trajectories where redundant visual patches are removed.<n>We show that ReVision reduces token usage by approximately 46% on average while improving success rate by 3% over the no drop baseline.<n>This suggests that the commonly observed saturation in visual history is not due to limited usefulness of past information, but rather a consequence of inefficient token representations.
• Score: 46.69118032596015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajectories grow, the token cost increases rapidly, limiting the amount of history that can be incorporated under fixed context and compute budgets. This has resulted in no or very limited improvement in the performance when using history unlike other domains. We address this inefficiency by introducing ReVision, which is used to train multimodal language models on trajectories where redundant visual patches are removed using a learned patch selector that compares patch representations across consecutive screenshots while preserving spatial structure required by the model. Across three benchmarks, OSWorld, WebTailBench, and AgentNetBench, when processing trajectories with 5 history screenshots using Qwen2.5-VL-7B, ReVision reduces token usage by approximately 46% on average while improving success rate by 3% over the no drop baseline. This establishes a clear efficiency gain, enabling agents to process longer trajectories with fewer tokens. With this improved efficiency, we revisit the role of history in CUAs and find that performance continues to improve as more past observations are incorporated when redundancy is removed. This suggests that the commonly observed saturation in visual history is not due to limited usefulness of past information, but rather a consequence of inefficient token representations.

Related papers

• SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models [25.951841702056544]
  multimodal large language models (MLLMs) incur substantial computational overhead when processing long visual token sequences.<n>We propose SinkPruner, a training-free visual token pruning framework for efficient MLLM inference.<n>SinkPruner follows a coarse-to-fine design with two key modules: a visual sanitizer that filters high-norm redundancies and alleviates attention sink and attention dispersion, and a text-guided pruner that further retains tokens semantically aligned with the text query.
  arXiv  Detail & Related papers  (2026-09-01T09:52:10Z)
• Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference [13.079143204091705]
  We study visual-token from an answer-observable perspective and find that late visual-token updates can remain large while having little effect on answer-token representations.<n>We propose an operator-level visual-token skipping framework that preserves the full visual-token sequence while selectively bypassing redundant attention, FFN, or both.
  arXiv  Detail & Related papers  (2026-06-30T16:08:29Z)
• Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives [20.029839773427298]
  We study token pruning for historical screenshots in GUI scenarios.<n>We find that GUI screenshots exhibit a distinctive foreground-background semantic composition.<n>We also observe that GUI Agents exhibit a recency effect similar to human cognition.
  arXiv  Detail & Related papers  (2026-03-27T03:21:19Z)
• How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need? [56.09721366421187]
  We present the finding that tokens are remarkably redundant, leading to substantial inefficiency.<n>We introduce gitmerge3D, a globally informed graph token merging method that can reduce the token count by up to 90-95%.<n>This work is the first to assess redundancy in large-scale 3D transformer models, providing insights into the development of more efficient 3D foundation architectures.
  arXiv  Detail & Related papers  (2025-11-07T17:38:01Z)
• Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention [50.97683288777336]
  Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens.<n>Recent studies have explored token pruning to alleviate this problem, which typically uses text-vision cross-attention.<n>We propose HoloV, a plug-and-play visual token pruning framework for efficient inference.
  arXiv  Detail & Related papers  (2025-10-03T11:33:40Z)
• A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models [94.49953824684853]
  We introduce a dynamic pruning framework, GlimpsePrune, inspired by human cognition.<n>It takes a data-driven ''glimpse'' and prunes irrelevant visual tokens in a single forward pass before answer generation.<n>An enhanced GlimpsePrune+ achieves 110% of the baseline performance while maintaining a similarly high pruning rate.
  arXiv  Detail & Related papers  (2025-08-03T02:15:43Z)
• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
  We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
  arXiv  Detail & Related papers  (2024-08-29T17:21:58Z)
• Explicit Visual Prompts for Visual Object Tracking [23.561539973210248]
  textbfEVPTrack is a visual tracking framework that exploits explicit visual prompts between consecutive frames. We show that our framework can achieve competitive performance at a real-time by exploiting both explicit and multi-scale information.
  arXiv  Detail & Related papers  (2024-01-06T07:12:07Z)
• AiluRus: A Scalable ViT Framework for Dense Prediction [95.1313839257891]
  Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. We propose to apply adaptive resolution for different regions in the image according to their importance. We evaluate our proposed method on three different datasets and observe promising performance.
  arXiv  Detail & Related papers  (2023-11-02T12:48:43Z)

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.