MARA (Retrieval-augmented generation): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by MMGraphRAG. Newer alternatives in the same sub-problem include VideoStir, Graph-to-Frame RAG, MG$^2$-RAG, AutoThinkRAG, AgenticOCR.

Method Drift›Retrieval-augmented generation

Tracked

MARA

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering

Retrieval-augmented generation · first seen Feb 1, 2026

current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.

VideoStir VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
Apr 7, 2026
Graph-to-Frame RAG Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
Apr 6, 2026
MG$^2$-RAG MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
Apr 4, 2026
AutoThinkRAG AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction
Mar 17, 2026
AgenticOCR AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
Feb 27, 2026
VimRAG VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Feb 13, 2026
FedMosaic FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters
Feb 5, 2026
MARA MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
Feb 1, 2026
LAD-RAG LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Oct 8, 2025