Comprendia: AI-Augmented Code Comprehension
Not on the map. Why?
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
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 32 references that are in the map. First posted on arXiv 10 Aug 2026.
Builds on
11 of 32 references.
References · 11
- 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
- 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
- 2022Using Pre-Trained Models to Boost Code Review Automationcited by 63
- 2024REPOFUSE: Repository-Level Code Completion with Fused Dual Contextcited by 32
- 2026LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loopscited by 8
- 2024Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Codecited by 5
- 2020The Vision of Software Clone Management: Past, Present, and Futurecited by 2
- 2025CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMscited by 2
- 2026When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requestscited by 2
- 2020Toward the Automatic Classification of Self-Affirmed Refactoringcited by 1
- 2025Decoding Dependency Risks: A Quantitative Study of Vulnerabilities in the Maven Ecosystemcited by 1
Built on by
Not cited yet.