引导内在之眼：一种用于层次化和灵活的视觉基础推理的框架
Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning
AI总结：
GRiP通过认知增强的强化学习框架，提升视觉基础推理的鲁棒性和灵活性，实现复杂场景下的高性能表现。
摘要：
能够通过动态地将推理基础固定在视觉证据上进行“图像思考”的模型代表了多模态AI的重大飞跃。然而，复制和推进这种能力是非平凡的，当前的方法往往陷入端到端强化学习（RL）的不稳定性与监督微调（SFT）的刚性之间。这导致了模型要么难以学习，要么缺乏处理复杂现实场景所需的认知灵活性。为了解决这一困境，我们引入GRiP（引导推理与感知），一种新的两阶段训练框架，通过显式引导模型的感知焦点和逻辑路径，培养出稳健且灵活的视觉基础推理能力。GRiP的核心在于其认知增强的RL阶段，其两个关键创新点是：（1）显著性加权IoU奖励，激励模型优先定位关键任务对象而非琐碎干扰物；（2）多启发式奖励，通过奖励多样但逻辑上有效的推理路径来鼓励认知灵活性。基于Qwen2.5-VL-7B模型初始化，GRiP在多个具有挑战性的基准测试中均实现了显著的性能提升。它在极具挑战性的TreeBench和V* Bench上取得了最先进的开放源代码模型结果，证明了其在复杂视觉推理中的有效性。我们的工作表明，超越简单奖励，而是通过具有认知启发的信号引导模型关注什么和如何思考，对于解锁多模态智能的下一层次至关重要。代码将被公开发布。
英文摘要：
Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped between the instability of end-to-end reinforcement learning (RL) and the rigidity of supervised fine-tuning (SFT). This leads to models that either struggle to learn or lack the cognitive flexibility required for complex, real-world scenes. To navigate this dilemma, we introduce GRiP (Guided Reasoning and Perception), a novel two-stage training framework that cultivates robust and flexible visual grounded reasoning by explicitly guiding the model's perceptual focus and logical pathways. GRiP's core lies in its cognitive-enhanced RL stage, which features two key innovations: (1) a Salience-Weighted IoU Reward that incentivizes the model to prioritize the localization of mission-critical objects over trivial distractors, and (2) a Multi-Heuristic Reward that encourages cognitive flexibility by rewarding diverse yet logically valid reasoning pathways. Initialized from the Qwen2.5-VL-7B model, GRiP demonstrates significant performance gains across multiple challenging benchmarks. It achieves state-of-the-art results among open-source models on the highly challenging TreeBench and V* Bench, proving its effectiveness in complex visual reasoning. Our work demonstrates that moving beyond simplistic rewards and instead guiding models with cognitively-inspired signals for what to see and how to think is crucial for unlocking the next level of multimodal intelligence. The code will be made publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
