Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents

arXiv:2606.07235 · cs.IR, cs.LG · Submitted 2026-06-05 · Read on arXiv

cs.IR, cs.LG

Submitted: 2026-06-05

Updated: 2026-10-02

Code: https://github.com/DorothyDUUU/G2_Reader

Terminology

• Consistency — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-VL Technical Report
• PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• ColPali: Efficient Document Retrieval with Vision Language Models
• LightRAG: Simple and Fast Retrieval-Augmented Generation
• RAG-Anything: All-in-One RAG Framework
• SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
• From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation
• MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
• Zep: A Temporal Knowledge Graph Architecture for Agent Memory
• MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs
• MinerU: An Open-Source Solution for Precise Document Content Extraction
• Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
• When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
• A Multi-Granularity Retrieval Framework for Visually-Rich Documents
• A-MEM: Agentic Memory for LLM Agents
• Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
• Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition