paper-with-me

홈 › Papers

VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning

2025-12-06 · Yuji Wang, Wenlong Liu, Jingxuan Niu, Haoji Zhang, Yansong Tang arxiv

Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while neglecting to design effective response mechanisms for handling unreliable or erroneous tool outputs. This limitation is particularly pronounced in referring and grounding tasks, where inaccurate detection tool predictions often mislead TiVR models into generating hallucinated reasoning. To address this issue, we propose the VG-Refiner, the first framework aiming at the tool-refined referring grounded reasoning. Technically, we introduce a two-stage think-rethink mechanism that enables the model to explicitly analyze and respond to tool feedback, along with a refinement reward that encourages effective correction in response to poor tool results. In addition, we propose two new metrics and establish fair evaluation protocols to systematically measure the refinement ability of current models. We adopt a small amount of task-specific data to enhance the refinement capability of VG-Refiner, achieving a significant improvement in accuracy and correction ability on referring and reasoning grounding benchmarks while preserving the general capabilities of the pretrained model.

📄 PDF Abstract BibTeX arXiv:2512.06373

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningVisual Reasoning

Similar Papers 제목 키워드 기반

Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos

2025-08-10 · Tuyen Tran, Thao Minh Le, Quang-Hung Le, Truyen Tran arxiv

Vision-language alignment in video must address the complexity of language, evolving interacting entities, their action chains, and semantic gaps between language and vision. This work introduces Planner-Refiner, a frame…

Referring Video Object Segmentation

B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation

2026-05-22 · Mario Markov, Stefan Maria Ailuro, Mohammad Mahdi, Luc Van Gool 외 arxiv

Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception to medical image analysis. For complex …

Reinforcement LearningScene Understanding

Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

2025-06-04 · Qing Jiang, Xingyu Chen, Zhaoyang Zeng, Junzhi Yu 외

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainabl…

ObjectReferring Expression

CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning

2025-10-03 · Qihua Dong, Luis Figueroa, Handong Zhao, Kushal Kafle 외 arxiv

Referring Expression Comprehension and Segmentation are critical tasks for assessing the integration of language understanding and image comprehension, serving as benchmarks for Multimodal Large Language Models (MLLMs) c…

Referring Expression

Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement

2022-10-27 · Ryosuke Sawata, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka 외

Although deep neural network (DNN)-based speech enhancement (SE) methods outperform the previous non-DNN-based ones, they often degrade the perceptual quality of generated outputs. To tackle this problem, we introduce a …

DenoisingSpeech Enhancement