# ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Era

arXiv: https://arxiv.org/abs/2604.27820 · HTML: https://mlsanity.com/paper/2604.27820/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [Active Context Compression: Autonomous Memory Management in LLM Agents](https://mlsanity.com/paper/2601.07190/) (2026)
- [From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills](https://mlsanity.com/paper/2604.24026/) (2026)
- [From Commands to Prompts: LLM-based Semantic File System for AIOS](https://mlsanity.com/paper/2410.11843/) (2024)
- [Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP](https://mlsanity.com/paper/2603.27277/) (2026)
- [Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale](https://mlsanity.com/paper/2602.05447/) (2026)
- [Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex Reasoning](https://mlsanity.com/paper/2602.02206/) (2026)

## Built on by (most cited first, 1 of 1)

- [SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval](https://mlsanity.com/paper/2606.00822/) (2026)

## Abstract (arXiv)

Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This fundamental mismatch forces agents to inject entire documents into their context window, wasting tokens on irrelevant content, compounding state across multi-turn loops, and broadcasting information indiscriminately across agent roles. We argue this is not a prompt engineering problem, not a retrieval problem, and not a compression problem: it is a format problem. We introduce OBJECTGRAPH (.og), a file format that reconceives the document as a typed, directed knowledge graph to be traversed rather than a string to be injected. OBJECTGRAPH is a strict superset of Markdown - every .md file is a valid .og file - requires no infrastructure beyond a two-primitive query protocol, and is readable by both humans and agents without tooling. We formalize the Document Consumption Problem, characterise six structural properties no existing format satisfies simultaneously, and prove OBJECTGRAPH satisfies all six. We further introduce the Progressive Disclosure Model, the Role-Scoped Access Protocol, and Executable Assertion Nodes as native format primitives. Empirical evaluation across five document classes and eight agent task types demonstrates up to 95.3 percent token reduction with no statistically significant degradation in task accuracy (p > 0.05). Transpiler fidelity reaches 98.7 percent content preservation on a held-out document benchmark.