# LogicLens: Leveraging Semantic Code Graph to explore Multi Repository large systems

arXiv: https://arxiv.org/abs/2601.10773 · HTML: https://mlsanity.com/paper/2601.10773/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://mlsanity.com/paper/2408.03910/) (2024)
- [A Survey on Large Language Models for Software Engineering](https://mlsanity.com/paper/2312.15223/) (2023)
- [Aroma: Code Recommendation via Structural Code Search](https://mlsanity.com/paper/1812.01158/) (2018)
- [A Toolkit for Generating Code Knowledge Graphs](https://mlsanity.com/paper/2002.09440/) (2020)

## Built on by (most cited first, 2 of 2)

- [OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling](https://mlsanity.com/paper/2608.05141/) (2026)
- [Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study](https://mlsanity.com/paper/2608.01507/) (2026)

## Abstract (arXiv)

Understanding large software systems is a challenging task, especially when code is distributed across multiple repositories and microservices. Developers often need to reason not only about the structure of the code, but also about its domain logic and runtime behaviors, which are typically implicit and scattered. We introduce LogicLens, a reactive conversational agent that assists developers in exploring complex software systems through a semantic multi-repository graph. This graph is built in a preprocessing step by combining syntactic code analysis, via AST parsing and repository traversal, with semantic enrichment using Large Language Models (LLMs). The resulting graph captures both structural elements, such as files, classes, and functions, as well as functional abstractions like domain entities, operations, and workflows. Once the graph is constructed, LogicLens enables developers to interact with it via natural language, dynamically retrieving relevant subgraphs and answering technical or functional queries. We present the architecture of the system, discuss emergent behaviors, and evaluate its effectiveness on real-world multi-repository scenarios. We demonstrate emergent capabilities including impact analysis and symptom-based debugging that arise naturally from the semantic graph structure.