# Comprendia: AI-Augmented Code Comprehension

arXiv: https://arxiv.org/abs/2608.10290 · HTML: https://mlsanity.com/paper/2608.10290/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops](https://mlsanity.com/paper/2603.23613/) (2026)
- [Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code](https://mlsanity.com/paper/2403.06675/) (2024)
- [When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests](https://mlsanity.com/paper/2602.19441/) (2026)
- [The Vision of Software Clone Management: Past, Present, and Future](https://mlsanity.com/paper/2005.01005/) (2020)
- [CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs](https://mlsanity.com/paper/2510.11536/) (2025)
- [Toward the Automatic Classification of Self-Affirmed Refactoring](https://mlsanity.com/paper/2009.09279/) (2020)
- [Decoding Dependency Risks: A Quantitative Study of Vulnerabilities in the Maven Ecosystem](https://mlsanity.com/paper/2503.22134/) (2025)

## Abstract (arXiv)

Comprendia is an Eclipse plugin that integrates structural dependency visualization with LLM-powered code explanation on a shared interactive graph for Java program comprehension. The tool rests on four pillars: (1) a multi-edge-type dependency graph with live search and multiple layouts; (2) LLM explanations grounded in Graph-Aware Callee Pruning (GACP), an auditable strategy that selects relevant callees using the same graph the developer navigates; (3) a clone-detection overlay that highlights duplication and suggests extract-to-parent refactoring opportunities; and (4) a CVE risk overlay powered by OSV.dev. GACP uses graph distance, inheritance collapse, and edge-type weighting to produce prompts that are reproducible across LLM families and traceable to visible graph nodes. We demonstrate Comprendia on a Java project containing known clones and vulnerabilities, showing how the unified graph substrate supports comprehension while keeping the developer in control. Screencast: https://youtu.be/1wlh_RYehzA