UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards

• URL: http://arxiv.org/abs/2604.14967v2
• Date: Fri, 17 Apr 2026 02:39:23 GMT
• Title: UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
• Abstract summary: Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge.<n>We propose UniDoc-RL, a unified reinforcement learning framework in which an LVLM agent jointly performs retrieval, reranking, active visual perception, and reasoning.<n>Experiments on three benchmarks demonstrate that UniDoc-RL consistently surpasses state-of-the-art baselines, yielding up to 17.7% gains over prior RL-based methods.
• Score: 16.669801835057424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems typically rely on generic retrieval signals that overlook the fine-grained visual semantics essential for complex reasoning. To address this limitation, we propose UniDoc-RL, a unified reinforcement learning framework in which an LVLM agent jointly performs retrieval, reranking, active visual perception, and reasoning. UniDoc-RL formulates visual information acquisition as a sequential decision-making problem with a hierarchical action space. Specifically, it progressively refines visual evidence from coarse-grained document retrieval to fine-grained image selection and active region cropping, allowing the model to suppress irrelevant content and attend to information-dense regions. For effective end-to-end training, we introduce a dense multi-reward scheme that provides task-aware supervision for each action. Based on Group Relative Policy Optimization (GRPO), UniDoc-RL aligns agent behavior with multiple objectives without relying on a separate value network. To support this training paradigm, we curate a comprehensive dataset of high-quality reasoning trajectories with fine-grained action annotations. Experiments on three benchmarks demonstrate that UniDoc-RL consistently surpasses state-of-the-art baselines, yielding up to 17.7% gains over prior RL-based methods.

Related papers

• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval [111.99106496142474]
  Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure.<n>Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents.<n>We propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation.
  arXiv  Detail & Related papers  (2026-03-07T15:17:22Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• Reinforcement Learning in Vision: A Survey [36.820183535103695]
  This survey offers a critical and up-to-date synthesis of the field.<n>We first formalize visual RL problems and trace the evolution of policy-optimization strategies.<n>We distill trends such as curriculum-driven training, preference-aligned diffusion, and unified reward modeling.
  arXiv  Detail & Related papers  (2025-08-11T17:08:55Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning [45.39372905700317]
  We introduce VRAG-RL, a novel RL framework tailored for complex reasoning across visually rich information.<n>With this framework, VLMs interact with search engines, autonomously sampling single-turn or multi-turn reasoning trajectories.<n>Our approach highlights key limitations of RL in RAG domains.
  arXiv  Detail & Related papers  (2025-05-28T06:30:51Z)
• One RL to See Them All: Visual Triple Unified Reinforcement Learning [92.90120580989839]
  We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables visual reasoning and perception tasks within a single training pipeline.<n>V-Triune comprises triple complementary components: Sample-Level Datashelf (to unify diverse task inputs), Verifier-Level Reward (to deliver custom rewards via specialized verifiers).<n>We introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune.
  arXiv  Detail & Related papers  (2025-05-23T17:41:14Z)
• ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents [27.90338725230132]
  ViDoSeek is a dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning.<n>We propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents.<n> Notably, ViDoRAG outperforms existing methods by over 10% on the competitive ViDoSeek benchmark.
  arXiv  Detail & Related papers  (2025-02-25T09:26:12Z)
• INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL [90.06845886194235]
  We propose a modified objective for model-based reinforcement learning (RL) We integrate a term inspired by variational empowerment into a state-space model based on mutual information. We evaluate the approach on a suite of vision-based robot control tasks with natural video backgrounds.
  arXiv  Detail & Related papers  (2022-04-18T23:09:23Z)

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.