Robust Hierarchical Structures for Agentic Document Analysis

arXiv:2609.33322 · cs.DB, cs.AI, cs.CL, cs.IR · Submitted 2026-09-27 · Read on arXiv

cs.DB, cs.AI, cs.CL, cs.IR

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/Ruiying-Ma/SHED

Terminology

• Robustness — 101× in this paper · explained in 5 episodes
• Accuracy — 75× in this paper · explained in 1 episode
• Core — 10× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• RAG — 8× in this paper · explained in 3 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Table of Contents — 6× in this paper
• Semantic Hierarchical Tree — 5× in this paper
• Retrieval-Augmented Generation — 4× in this paper
• Agent Skills — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Two-Stage Framework — 3× in this paper · explained in 2 episodes
• Agentic Retrieval — 2× in this paper · explained in 1 episode
• Cognitive Load — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Query Complexity — 1× in this paper · explained in 2 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
• Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks
• Nougat: Neural Optical Understanding for Academic Documents
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• FinanceBench: A New Benchmark for Financial Question Answering
• Distilling Knowledge from Reader to Retriever for Question Answering
• Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser
• ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts
• DocBank: A Benchmark Dataset for Document Layout Analysis
• StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
• Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
• Visual Template Inference for Data Extraction from Documents
• A Declarative System for Optimizing AI Workloads
• MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
• pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs
• DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
• AgenticData: An Agentic Data Analytics System for Heterogeneous Data

Related papers

• Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
• Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
• Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation
• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
• MaDI-Bench: An End-to-End Data Integration Benchmark
• Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning