mlsanityData to 7 Oct 2026

Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale

arXiv 2602.05447 ↗First posted 5 Feb 2026cs.CL cs.AIcited by 4

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large Language Model agents increasingly operate external systems through programmatic interfaces, yet practitioners lack empirical guidance on how to structure the context these agents consume. Using SQL generation as a proxy for programmatic agent operations, we present a systematic study of context engineering for structured data, comprising 9,649 experiments across 11 models, 4 formats (YAML, Markdown, JSON, Token-Oriented Object Notation [TOON]), and schemas ranging from 10 to 10,000 tables. Our findings challenge common assumptions. First, architecture choice is model-dependent: file-based context retrieval improves accuracy for frontier-tier models (Claude, GPT, Gemini; +2.7%, p=0.029) but shows mixed results for open source models (aggregate -7.7%, p<0.001), with deficits varying substantially by model. Second, format does not significantly affect aggregate accuracy (chi-squared=2.45, p=0.484), though individual models, particularly open source, exhibit format-specific sensitivities. Third, model capability is the dominant factor, with a 21 percentage point accuracy gap between frontier and open source tiers that dwarfs any format or architecture effect. Fourth, file-native agents scale to 10,000 tables through domain-partitioned schemas while maintaining high navigation accuracy. Fifth, file size does not predict runtime efficiency: compact or novel formats can incur a token overhead driven by grep output density and pattern unfamiliarity, with the magnitude depending on model capability. These findings provide practitioners with evidence-based guidance for deploying LLM agents on structured systems, demonstrating that architectural decisions should be tailored to model capability rather than assuming universal best practices.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 16 of its 22 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

16 of 22 references.

References · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  6. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  9. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  10. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  11. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  12. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
4 more
  1. 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 132
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  3. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  4. 2025Context Engineering for AI Agents in Open-Source Softwarecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Harness Engineering for Agentic AI Coding Tools: An Exploratory Studycited by 10
  2. 2026Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variablescited by 2
  3. 2026ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Eracited by 1
  4. 2026The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deploymentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents
  2. 2026Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets
  3. 2026PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
  4. 2026The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems
  5. 2025Readme_AI: Dynamic Context Construction for Large Language Models
  6. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
  7. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
  8. 2025Everything is Context: Agentic File System Abstraction for Context Engineering