Tag
MCite-RL is a citation-enhanced agentic reinforcement learning framework designed for reliable multimodal RAG, introducing iterative retrieval and reasoning for visual citations and a reward mechanism to jointly optimize answer accuracy and source traceability.
Introduces QIMG-7, a benchmark for multimodal retrieval pollution in factual QA, and proposes Source-Aware Trust Resolution (SATR), a training-free method improving robustness over naive fusion.
Introduces MODE-RAG, a multi-agent system using Variational Free Energy and Monte Carlo Tree Search to dynamically gate interventions for mitigating hallucinations in Multimodal Retrieval-Augmented Generation systems, along with the ModeVent evaluation dataset.
MM-BizRAG is a multimodal retrieval-augmented generation system for enterprise Q&A that uses document structure-aware splitting and layout-aware parsing to outperform vision-centric baselines by up to 32% on heterogeneous enterprise documents. The paper also introduces FastRAGEval, a cost-efficient LLM-based evaluation metric with stronger human alignment than RAGChecker.
This paper introduces GranuVistaVQA, a multimodal benchmark with element-level annotations, and GranuRAG, a framework that treats visual elements as first-class retrieval units for verifiable multimodal RAG, achieving up to 29.2% improvement over baselines.
This paper presents KITE, a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system for algorithmic reasoning and problem-solving in AI education. The system uses intent-aware Socratic response strategies and multimodal RAG to provide course-grounded, pedagogically appropriate feedback, and is evaluated through metrics, expert review, and simulated student interactions.