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

• URL: http://arxiv.org/abs/2605.23500v1
• Date: Fri, 22 May 2026 11:04:12 GMT
• Title: B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation
• Abstract summary: We introduce group relative tool optimization (GRTO) for jointly optimizing a policy with differentiable tool use.<n> GRTO reuses group relative policy optimization (GRPO) rollouts to optimize the auxiliary tool objective, letting decoder gradients complement policy rewards.<n>B-GRTO results in substantial improvements over plain GRPO, matching or surpassing domain-specific state-of-the-art methods.
• Score: 52.210953881548996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 referring segmentation, recent methods pair large vision-language models with segmentation decoders: the former analyzes the image and prompt, while the latter predicts the target mask. Although reinforcement learning improves reasoning-intensive vision-language systems, trainable tools such as segmentation decoders are typically optimized separately with differentiable objectives, and the principled integration of such objectives into reinforcement learning remains underexplored. Thus, we introduce group relative tool optimization (GRTO), a mathematically grounded framework for jointly optimizing a policy with differentiable tool use. GRTO reuses group relative policy optimization (GRPO) rollouts to optimize the auxiliary tool objective, letting decoder gradients complement policy rewards. Further, we derive Bootstrapped-GRTO (B-GRTO), a pre-training method that cheaply bootstraps the tool, leading to faster convergence and superior performance. Across three challenging referring segmentation settings, B-GRTO results in substantial improvements over plain GRPO, matching or surpassing domain-specific state-of-the-art methods. This demonstrates the value of unifying reinforcement learning with differentiable auxiliary objectives for reasoning-intensive segmentation.

Related papers

• Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization [54.855135506924775]
  We introduce a two-stage multi-objective optimization framework for aligning tool-using large language models (LLMs) under competing objectives.<n>This design enables fine-grained, action-level optimization across multiple conflicting objectives.
  arXiv  Detail & Related papers  (2026-06-15T01:58:07Z)
• Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization [7.961090665261694]
  We propose Graph-GRPO, a novel topology optimization framework that integrates Group Relative Policy Optimization.<n>By normalizing rewards across the sampled group, our method effectively mitigates the noise derived from task difficulty variance and enables fine-grained credit assignment.
  arXiv  Detail & Related papers  (2026-03-03T07:45:40Z)
• TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization [97.18886232580131]
  Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration.<n>We propose Turn-Level GRPO, a lightweight RL algorithm that performs turn-level group sampling for fine-grained optimization.
  arXiv  Detail & Related papers  (2026-01-23T06:21:33Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• A Deep Learning Framework for Boundary-Aware Semantic Segmentation [9.680285420002516]
  This study proposes a Mask2Former-based semantic segmentation algorithm incorporating a boundary enhancement feature bridging module (BEFBM)<n>The proposed approach achieves significant improvements in metrics such as mIOU, mDICE, and mRecall.<n>Visual analysis confirms the model's advantages in fine-grained regions.
  arXiv  Detail & Related papers  (2025-03-28T00:00:08Z)
• SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketches [116.1810651297801]
  SketchYourSeg establishes freehand sketches as a powerful query modality for subjective image segmentation.<n>Our evaluations demonstrate superior performance over existing approaches across diverse benchmarks.
  arXiv  Detail & Related papers  (2025-01-27T13:07:51Z)
• Pair then Relation: Pair-Net for Panoptic Scene Graph Generation [54.92476119356985]
  Panoptic Scene Graph (PSG) aims to create a more comprehensive scene graph representation using panoptic segmentation instead of boxes. Current PSG methods have limited performance, which hinders downstream tasks or applications. We present a novel framework: Pair then Relation (Pair-Net), which uses a Pair Proposal Network (PPN) to learn and filter sparse pair-wise relationships between subjects and objects.
  arXiv  Detail & Related papers  (2023-07-17T17:58:37Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• Generalizing Interactive Backpropagating Refinement for Dense Prediction [0.0]
  We introduce a set of G-BRS layers that enable both global and localized refinement for a range of dense prediction tasks. Our method can successfully generalize and significantly improve performance of existing pretrained state-of-the-art models with only a few clicks.
  arXiv  Detail & Related papers  (2021-12-21T03:52:08Z)
• Visual Object Tracking by Segmentation with Graph Convolutional Network [7.729569666460712]
  We propose to utilize graph convolutional network (GCN) model for superpixel based object tracking. The proposed model provides a general end-to-end framework which integrates i) label linear prediction, and ii) structure-aware feature information of each superpixel together.
  arXiv  Detail & Related papers  (2020-09-05T12:43:21Z)

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.