DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

• URL: http://arxiv.org/abs/2505.14362v2
• Date: Mon, 26 May 2025 13:19:11 GMT
• Title: DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
• Authors: Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, Xing Yu,
• Abstract summary: DeepEyes is a model with "thinking with images" capabilities incentivized through end-to-end reinforcement learning.<n>We propose a tool-use-oriented data selection mechanism and a reward strategy to encourage successful tool-assisted reasoning trajectories.<n>DeepEyes achieves significant performance gains on fine-grained perception and reasoning benchmarks.
• Score: 11.242852367476015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Vision-Language Models (VLMs) have shown strong capabilities in multimodal understanding and reasoning, yet they are primarily constrained by text-based reasoning processes. However, achieving seamless integration of visual and textual reasoning which mirrors human cognitive processes remains a significant challenge. In particular, effectively incorporating advanced visual input processing into reasoning mechanisms is still an open question. Thus, in this paper, we explore the interleaved multimodal reasoning paradigm and introduce DeepEyes, a model with "thinking with images" capabilities incentivized through end-to-end reinforcement learning without the need for cold-start SFT. Notably, this ability emerges natively within the model itself, leveraging its inherent grounding ability as a tool instead of depending on separate specialized models. Specifically, we propose a tool-use-oriented data selection mechanism and a reward strategy to encourage successful tool-assisted reasoning trajectories. DeepEyes achieves significant performance gains on fine-grained perception and reasoning benchmarks and also demonstrates improvement in grounding, hallucination, and mathematical reasoning tasks. Interestingly, we observe the distinct evolution of tool-calling behavior from initial exploration to efficient and accurate exploitation, and diverse thinking patterns that closely mirror human visual reasoning processes. Code is available at https://github.com/Visual-Agent/DeepEyes.

Related papers

• Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation [52.6091162517921]
  INSIGHT is a two-stage framework for egocentric action anticipation.<n>In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions.<n>In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning.
  arXiv  Detail & Related papers  (2025-08-03T12:52:27Z)
• Reasoning in machine vision: learning to think fast and slow [10.430190333487957]
  Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex and unfamiliar scenarios.<n>Machine intelligence remains bound to training data, lacking the ability to dynamically refine solutions at inference time.<n>Here we present a novel learning paradigm that enables machine reasoning in vision by allowing performance improvement with increasing thinking time.
  arXiv  Detail & Related papers  (2025-06-27T10:03:05Z)
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
  We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning [18.13538667261998]
  Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background.<n>We build a visual system that mimicks human visual camouflaged perception to progressively and iteratively refocus' visual concealed content.
  arXiv  Detail & Related papers  (2025-05-26T07:27:18Z)
• VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search [89.43196232124883]
  VisuoThink is a novel framework that seamlessly integrates visuospatial and linguistic domains.<n>It enables progressive visual-textual reasoning and incorporates test-time scaling through look-ahead tree search.
  arXiv  Detail & Related papers  (2025-04-12T08:37:30Z)
• A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs [3.2228025627337864]
  This paper introduces a structured evaluation framework to dissect the perception-reasoning interface in Vision-Language Models (VLMs)<n>We propose three distinct evaluation paradigms, mirroring human problem-solving strategies.<n>Applying this framework, we demonstrate that CA, leveraging powerful language models for reasoning over rich, independently generated descriptions, achieves new state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2025-01-23T12:42:42Z)
• Imagine while Reasoning in Space: Multimodal Visualization-of-Thought [70.74453180101365]
  Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs)<n>We propose a new reasoning paradigm, Multimodal Visualization-of-Thought (MVoT)<n>It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces.
  arXiv  Detail & Related papers  (2025-01-13T18:23:57Z)
• Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios [69.00444996464662]
  We propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables vision-language models to reason using visual crops corresponding to relevant entities.<n>Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting.
  arXiv  Detail & Related papers  (2025-01-08T18:31:16Z)
• LATTE: Learning to Think with Vision Specialists [103.5952731807559]
  We propose LATTE, a family of vision-language models that offload perception to state-of-the-art vision models.<n>By offloading perception to state-of-the-art vision models, our approach enables vision-language models to focus solely on reasoning over high-quality perceptual information.
  arXiv  Detail & Related papers  (2024-12-07T00:42:04Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)
• Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker [72.09076317574238]
  ToM is a plug-and-play approach to investigate the belief states of characters in reading comprehension. We show that ToM enhances off-the-shelf neural network theory mind in a zero-order setting while showing robust out-of-distribution performance compared to supervised baselines.
  arXiv  Detail & Related papers  (2023-06-01T17:24:35Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)

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.