MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning

• URL: http://arxiv.org/abs/2608.21808v1
• Date: Sat, 22 Aug 2026 07:04:18 GMT
• Title: MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning
• Abstract summary: MCite-RL is a citation-enhanced agentic reinforcement learning framework for reliable multimodal RAG.<n>MCite-RL incorporates a Citation-enhanced Reward mechanism that integrates both process-level and outcome-level feedback.<n>In experiments on benchmarks such as Wiki-VISA, FinRAGBench-V, and MMLongBench-Doc, MCite-RL effectively achieves the joint optimization of citation precision and answer quality.
• Score: 18.62756269233221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Retrieval-Augmented Generation (RAG) with visual citation is crucial for ensuring the traceability and verifiability of MLLMs. However, current RAG and SFT-based methods struggle to achieve robust cross-modal reasoning, causing imprecise visual citations or decoupling between the citation and the generated answers. To address these limitations, we propose MCite-RL, a citation-enhanced agentic reinforcement learning framework designed for reliable multimodal RAG. MCite-RL introduces an Agentic Refinement module for visual citation that employs iterative retrieval, reasoning, and recursive cropping to progressively narrow the search space, transforming citation into a dynamic, evidence-driven reasoning process rather than a static step. Furthermore, we incorporate a Citation-enhanced Reward mechanism that integrates both process-level and outcome-level feedback within a reinforcement learning paradigm to jointly optimize answer accuracy and source traceability. Extensive experiments on benchmarks such as Wiki-VISA, FinRAGBench-V, and MMLongBench-Doc demonstrate that MCite-RL effectively achieves the joint optimization of citation precision and answer quality.

Related papers

• V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval [32.5242219186118]
  We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection.<n>V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification.
  arXiv  Detail & Related papers  (2026-02-05T18:59:21Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification [41.99844472131922]
  This research introduces VeriFact-CoT, a novel method designed to address the pervasive issues of hallucination and the absence of credible citation sources in Large Language Models (LLMs)<n>By incorporating a multi-stage mechanism of 'fact verification-reflection-citation integration,' VeriFact-CoT empowers LLMs to critically self-examine and revise their intermediate reasoning steps and final answers.
  arXiv  Detail & Related papers  (2025-09-06T15:07:59Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• On the Capacity of Citation Generation by Large Language Models [38.47160164251295]
  Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-15T03:04:26Z)
• Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation [51.8188846284153]
  Attributed Text Generation (ATG) is proposed to enhance credibility and verifiability in RAG systems.<n>This paper proposes ReClaim, a fine-grained ATG method that alternates the generation of references and answers step by step.<n>With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.
  arXiv  Detail & Related papers  (2024-07-01T20:47:47Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)

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.