RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations

• URL: http://arxiv.org/abs/2512.24023v1
• Date: Tue, 30 Dec 2025 06:50:11 GMT
• Title: RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations
• Authors: Xingqi He, Yujie Zhang, Shuyong Gao, Wenjie Li, Lingyi Hong, Mingxi Chen, Kaixun Jiang, Jiyuan Fu, Wenqiang Zhang,
• Abstract summary: We propose RSAgent, an agentic Multimodal Large Language Model (MLLM) which interleaves reasoning and action for segmentation via multi-turn tool invocations.<n> RSAgent queries a segmentation toolbox, observes visual feedback, and revises its spatial hypothesis using historical observations to re-localize targets and iteratively refine masks.<n>Extensive experiments show that RSAgent achieves a zero-shot performance of 66.5% gIoU on ReasonSeg test, improving over Seg-Zero-7B by 9%, and reaches 81.5% cIoU on RefCOCOg, demonstrating state-of-the-art performance
• Score: 52.752467948588816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat text-guided segmentation as one-shot grounding, where the model predicts pixel prompts in a single forward pass to drive an external segmentor, which limits verification, refocusing and refinement when initial localization is wrong. To address this limitation, we propose RSAgent, an agentic Multimodal Large Language Model (MLLM) which interleaves reasoning and action for segmentation via multi-turn tool invocations. RSAgent queries a segmentation toolbox, observes visual feedback, and revises its spatial hypothesis using historical observations to re-localize targets and iteratively refine masks. We further build a data pipeline to synthesize multi-turn reasoning segmentation trajectories, and train RSAgent with a two-stage framework: cold-start supervised fine-tuning followed by agentic reinforcement learning with fine-grained, task-specific rewards. Extensive experiments show that RSAgent achieves a zero-shot performance of 66.5% gIoU on ReasonSeg test, improving over Seg-Zero-7B by 9%, and reaches 81.5% cIoU on RefCOCOg, demonstrating state-of-the-art performance on both in-domain and out-of-domain benchmarks.

Related papers

• RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation [71.2136732268131]
  RGB-Thermal (RGBT) tracking aims to achieve robust object localization across diverse environmental conditions.<n>Existing RGBT trackers rely solely on initial-frame visual information for target modeling.<n>We propose RAGTrack, a novel Retrieval-Augmented Generation framework for robust RGBT tracking.
  arXiv  Detail & Related papers  (2026-03-04T01:02:04Z)
• Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning [63.109585527799005]
  GroundingAgent is a visual grounding framework that operates without task-specific fine-tuning.<n>It achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks.<n>It also offers strong interpretability, transparently illustrating each reasoning step.
  arXiv  Detail & Related papers  (2025-11-24T03:11:08Z)
• Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing [55.291219073365546]
  Open-Vocabulary Remote Sensing Image (OVRSIS) is an emerging task that adapts Open-Vocabulary (OVS) to the remote sensing (RS) domain.<n>textbfRSKT-Seg is a novel open-vocabulary segmentation framework tailored for remote sensing.<n> RSKT-Seg consistently outperforms strong OVS baselines by +3.8 mIoU and +5.9 mACC, while achieving 2x faster inference through efficient aggregation.
  arXiv  Detail & Related papers  (2025-09-15T15:24:49Z)
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models [60.713908578319256]
  We propose Direct Discrepancy Learning (DDL) to optimize the detector with task-oriented knowledge.<n>Built upon this, we introduce DetectAnyLLM, a unified detection framework that achieves state-of-the-art MGTD performance.<n>MIRAGE samples human-written texts from 10 corpora across 5 text-domains, which are then re-generated or revised using 17 cutting-edge LLMs.
  arXiv  Detail & Related papers  (2025-09-15T10:59:57Z)
• Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation [61.37076111486196]
  Ref-AVS aims to segment target objects in audible videos based on given reference expressions.<n>We propose TGS-Agent, which decomposes the task into a Think-Ground-Segment process.<n>Ref-Thinker is a multimodal language model capable of reasoning over textual, visual, and auditory cues.
  arXiv  Detail & Related papers  (2025-08-06T13:05:09Z)
• Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning [38.375639439367255]
  Seg-R1 is a preliminary exploration of using reinforcement learning to enhance the pixel-level understanding and reasoning capabilities of large multimodal models.<n>We introduce Group Relative Policy Optimization into the segmentation domain, equipping the LMM with pixel-level comprehension.<n>Seg-R1 achieves remarkable performance with purely RL-based training, achieving.873 S-measure on COD10K without complex model modification.
  arXiv  Detail & Related papers  (2025-06-27T20:40:45Z)
• AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensing [12.91626624625134]
  Few-shot (FSS) aims to segment the interested objects in the query image with just a handful of labeled samples (i.e., support images) Previous schemes would leverage the similarity between support-Query pixel pairs to construct the pixel-level semantic correlation. In remote sensing scenarios with extreme intra-class variations and cluttered backgrounds, such pixel-level correlations may produce tremendous mismatches. We propose a novel Agent Mining Transformer (AgMTR), which adaptively mines a set of local-aware agents to construct agent-level semantic correlation.
  arXiv  Detail & Related papers  (2024-09-26T01:12:01Z)
• You Only Look at Once for Real-time and Generic Multi-Task [20.61477620156465]
  A-YOLOM is an adaptive, real-time, and lightweight multi-task model. We develop an end-to-end multi-task model with a unified and streamlined segmentation structure. We achieve competitive results on the BDD100k dataset.
  arXiv  Detail & Related papers  (2023-10-02T21:09:43Z)
• SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression [6.74412860849373]
  We propose SRFormer, a unified DETR-based model with amalgamated and Regression. Our empirical analysis indicates that favorable segmentation predictions can be obtained at the initial decoder layers. Our method's exceptional robustness, superior training and data efficiency, as well as its state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-08-21T07:34:31Z)

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.