A meta-agent uses failure analysis to evolve a task agent's instructions for coordinating lexical, semantic, and multimodal retrievers, leading to up to 19.6 point gains on document QA benchmarks.
Mdocagent: A multi-modal multi-agent framework for document understanding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
DocPrune is a training-free token pruning method that removes background and irrelevant tokens from document images using question and comprehension signals, yielding 3x encoder and 3.3x decoder throughput gains plus +1 F1 on M3DocRAG.
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
A survey of MLLM-based Visually Rich Document Understanding covering feature integration techniques, training paradigms, challenges like data scarcity, and emerging trends such as RAG and agentic frameworks.
citing papers explorer
-
Hybrid Retriever Evolution for Multimodal Document Reasoning Agents
A meta-agent uses failure analysis to evolve a task agent's instructions for coordinating lexical, semantic, and multimodal retrievers, leading to up to 19.6 point gains on document QA benchmarks.
-
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
-
DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
DocPrune is a training-free token pruning method that removes background and irrelevant tokens from document images using question and comprehension signals, yielding 3x encoder and 3.3x decoder throughput gains plus +1 F1 on M3DocRAG.
-
EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
-
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends
A survey of MLLM-based Visually Rich Document Understanding covering feature integration techniques, training paradigms, challenges like data scarcity, and emerging trends such as RAG and agentic frameworks.