mlsanityData to 14 Oct 2026

Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework

arXiv 2508.12257 ↗First posted 17 Aug 2025cs.CLcited by 2

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal evaluation framework for structured outputs, establishing text-to-structure as foundational infrastructure for next-generation AI systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 98 of its 156 references that are in the map. First posted on arXiv 17 Aug 2025.

Builds on

98 of 156 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs13 Jul
  2. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents23 Jun
  3. 2025Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks18 Feb
  4. 2025Top Ten Challenges Towards Agentic Neural Graph Databases24 Jan
  5. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG15 Jan
  6. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents17 Oct
  7. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning9 Sep
  8. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation5 Oct

Other references · 90

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  9. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  10. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 722
  11. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  12. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 408
38 more
  1. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  2. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  3. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 322
  4. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
  5. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  6. 2023Mathematical Capabilities of ChatGPTcited by 268
  7. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
  8. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  9. 2017Challenges in Data-to-Document Generationcited by 226
  10. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  11. 2023Large Language Models for Generative Information Extraction: A Surveycited by 185
  12. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 170
  13. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 169
  14. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 160
  15. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  16. 2024ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoningcited by 128
  17. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  18. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  19. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  20. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  21. 2022ChatGPT: The End of Online Exam Integrity?cited by 88
  22. 2020Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Modelcited by 78
  23. 2023Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Methodcited by 76
  24. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  25. 2023ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Languagecited by 73
  26. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  27. 2024ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoningcited by 68
  28. 2024TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learningcited by 52
  29. 2024NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surroundingcited by 51
  30. 2025KGGen: Extracting Knowledge Graphs from Plain Text with Language Modelscited by 49
  31. 2023Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Textcited by 48
  32. 2021Text-to-Table: A New Way of Information Extractioncited by 47
  33. 2019Data-to-text Generation with Entity Modelingcited by 45
  34. 2023Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statementscited by 44
  35. 2018Table-to-Text: Describing Table Region with Natural Languagecited by 41
  36. 2023PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Modelscited by 37
  37. 2024GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theorycited by 37
  38. 2023Instruct and Extract: Instruction Tuning for On-Demand Information Extractioncited by 36

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understandingcited by 4
  2. 2026MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  2. 2025Model-Document Protocol for AI Search
  3. 2026The Path Ahead for Agentic AI: Challenges and Opportunities
  4. 2026NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track
  5. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
  6. 2026Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
  7. 2026A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
  8. 2026MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition