# Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants

arXiv: https://arxiv.org/abs/2601.10112 · HTML: https://mlsanity.com/paper/2601.10112/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [RepoFusion: Training Code Models to Understand Your Repository](https://mlsanity.com/paper/2306.10998/) (2023)
- [CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support](https://mlsanity.com/paper/2407.16148/) (2024)
- [Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks](https://mlsanity.com/paper/2505.16901/) (2025)
- [HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information](https://mlsanity.com/paper/2203.09629/) (2022)
- [On the Impacts of Contexts on Repository-Level Code Generation](https://mlsanity.com/paper/2406.11927/) (2024)
- [M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation](https://mlsanity.com/paper/2410.21157/) (2024)
- [Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets](https://mlsanity.com/paper/2503.17502/) (2025)
- [NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization](https://mlsanity.com/paper/2505.24575/) (2025)
- [Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs](https://mlsanity.com/paper/2501.07857/) (2025)
- [MetaFFI -- Multilingual Indirect Interoperability System](https://mlsanity.com/paper/2408.14175/) (2024)

## Built on by (most cited first, 4 of 4)

- [Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable](https://mlsanity.com/paper/2607.13285/) (2026)
- [Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP](https://mlsanity.com/paper/2603.27277/) (2026)
- [CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents](https://mlsanity.com/paper/2607.25431/) (2026)
- [The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning](https://mlsanity.com/paper/2608.26602/) (2026)

## Abstract (arXiv)

Repository aware coding agents often struggle to recover build and test structure, especially in multilingual projects where cross language dependencies are encoded across heterogeneous build systems and tooling. We introduce the Repository Intelligence Graph (RIG), a deterministic, evidence backed architectural map that represents buildable components, aggregators, runners, tests, external packages, and package managers, connected by explicit dependency and coverage edges that trace back to concrete build and test definitions. We also present SPADE, a deterministic extractor that constructs RIG from build and test artifacts (currently with an automatic CMake plugin based on the CMake File API and CTest metadata), and exposes RIG as an LLM friendly JSON view that agents can treat as the authoritative description of repository structure. We evaluate three commercial agents (Claude Code, Cursor, Codex) on eight repositories spanning low to high build oriented complexity, including the real world MetaFFI project. Each agent answers thirty structured questions per repository with and without RIG in context, and we measure accuracy, wall clock completion time, and efficiency (seconds per correct answer). Across repositories and agents, providing RIG improves mean accuracy by 12.2% and reduces completion time by 53.9%, yielding a mean 57.8% reduction in seconds per correct answer. Gains are larger in multilingual repositories, which improve by 17.7% in accuracy and 69.5% in efficiency on average, compared to 6.6% and 46.1% in single language repositories. Qualitative analysis suggests that RIG shifts failures from structural misunderstandings toward reasoning mistakes over a correct structure, while rare regressions highlight that graph based reasoning quality remains a key factor.