DRAgent: Discriminative Reasoning Agent for Referring Expression Segmentation

• URL: http://arxiv.org/abs/2608.22885v1
• Date: Mon, 24 Aug 2026 07:18:38 GMT
• Title: DRAgent: Discriminative Reasoning Agent for Referring Expression Segmentation
• Abstract summary: DRAgent is an MLLM-driven discriminative reasoning framework for Referring Expression.<n>DRAgent achieves competitive performance on RefCOCO, RefCOCO+, and RefCOCOg.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Referring Expression Segmentation (RES) aims to generate a pixel-level mask for the object specified by a language expression. Recent methods based on multimodal large language models (MLLMs) often rely on one-pass coordinate prediction for visual localization, which serializes continuous spatial locations as discrete text tokens and may lead to localization bias and alignment errors. To address these issues, we propose DRAgent, an MLLM-driven discriminative reasoning (DR) framework for RES. Instead of requiring the MLLM to generate localization coordinates, DRAgent first constructs a detector-generated candidate space and then uses the MLLM as a visual-semantic target discriminator. Specifically, the MLLM performs reliable target selection among potential distractors through a two-stage DR mechanism, which first screens high-recall candidates and then performs instance-wise verification. The selected target box is subsequently used as a spatial prompt for a foundation segmentation model to produce the final pixel-level mask. Furthermore, we construct a self-consistency-filtered reasoning-chain data pipeline for LoRA-based fine-tuning, providing more reliable supervision for enhancing the MLLM's discriminative reasoning capability. Experiments demonstrate that DRAgent achieves competitive performance on RefCOCO, RefCOCO+, and RefCOCOg.

Related papers

• ProtoRAG: Prototype-Based Retrieval Augmentation for Few-Shot Fine-Grained Remote Sensing Object Detection [14.475375107679731]
  Few-shot fine-grained object detection in remote sensing imagery is challenging because limited annotations must support both object localization and discrimination.<n>We propose ProtoRAG, a prototype-based retrieval-augmented framework that decouples coarse localization from fine-grained recognition.<n>We develop an uncertainty-guided candidate-constrained reasoning strategy that augments MLLMs with retrieved candidate-specific visual references.
  arXiv  Detail & Related papers  (2026-09-05T07:40:19Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs [55.44696796126619]
  Earth Observation systems are designed to support domain experts who often express their requirements through vague natural language.<n>A practical EO AI system must bridge the gap between ambiguous human queries and the appropriate multi-granularity visual analysis tasks.<n>We propose RemoteAgent, an agentic framework that strategically respects the capability intrinsic boundaries of MLLMs.
  arXiv  Detail & Related papers  (2026-04-09T03:40:46Z)
• Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation [40.66340261994875]
  textbfDSS is a progressive framework designed to refine segmentation step by step.<n>It achieves state-of-the-art performance on multiple COS benchmarks, especially in multiple-instance scenes.
  arXiv  Detail & Related papers  (2026-02-23T15:15:37Z)
• AgenticTagger: Structured Item Representation for Recommendation with LLM Agents [58.12004213978182]
  AgenticTagger is a framework that queries LLMs for representing items with sequences of text descriptors.<n>To effectively and efficiently ground vocabulary in the item corpus of interest, we design a multi-agent reflection mechanism.<n>Experiments on public and private data show AgenticTagger brings consistent improvements across diverse recommendation scenarios.
  arXiv  Detail & Related papers  (2026-02-05T18:01:37Z)
• ResAgent: Entropy-based Prior Point Discovery and Visual Reasoning for Referring Expression Segmentation [21.87321809019825]
  Referring Expression (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions.<n>textbfmodel is a novel RES framework integrating textbfEntropy-textbfBased Point textbfDiscovery (textbfEBD) and textbfVision-textbfBased textbfReasoning (textbfVBR)<n>model implements a coarse-to
  arXiv  Detail & Related papers  (2026-01-23T01:56:04Z)
• 1 + 1 > 2: Detector-Empowered Video Large Language Model for Spatio-Temporal Grounding and Reasoning [53.28271278708241]
  We present a Detector-Empowered Video LLM, short for DEViL.<n> DEViL couples a Video LLM with an open-vocabulary detector (OVD)<n>Unlike tokens that merely serve as spatial prompts or segmentor switches, the RST functions as both a control signal and a replacement for the OVD's text embedding.
  arXiv  Detail & Related papers  (2025-12-07T06:11:15Z)
• 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)
• GSVA: Generalized Segmentation via Multimodal Large Language Models [72.57095903188922]
  Generalized Referring Expression (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image. Current solutions to GRES remain unsatisfactory since segmentation MLLMs cannot correctly handle the cases where users might reference multiple subjects in a singular prompt. We propose Generalized Vision Assistant (GSVA) to address this gap.
  arXiv  Detail & Related papers  (2023-12-15T02:54:31Z)

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.