Code2UML: Agentic LLMs with context engineering for scalable software visualization
- URL: http://arxiv.org/abs/2605.24453v1
- Date: Sat, 23 May 2026 08:01:26 GMT
- Title: Code2UML: Agentic LLMs with context engineering for scalable software visualization
- Abstract summary: This paper introduces an agentic architecture with context engineering for automated diagram generation from source code repositories.<n>It employs a hierarchy of five specialized agents: PlannerAgent, Analyzer DiagramAgent, CorrectorAgent and DependencyAnalyzerAgent, built on the Claude Agent SDK.<n>A deterministic, importance-weighted IR compaction layer transforms full project IRs into diagram-specific views guaranteed to fit within token constraints.
- Score: 7.069738194755401
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Model (LLM)-based code analysis tools are adopted to automate software documentation tasks. However, the scalability of these approaches to real codebases, where Intermediate Representations (IR) exceed LLM context limits, remains underexplored. This paper introduces an agentic architecture with context engineering for automated UML diagram generation from source code repositories. It employs a hierarchy of five specialized agents: PlannerAgent, AnalyzerAgent, DiagramAgent, CorrectorAgent and DependencyAnalyzerAgent, built on the Claude Agent SDK, each addressing a distinct cognitive subtask. A deterministic, importance-weighted IR compaction layer transforms full project IRs into diagram-specific views guaranteed to fit within token constraints, requiring no LLM calls and completing in milliseconds. Thus, we evaluate the system across 12 open-source repositories in 4 programming languages (Java, JavaScript, PHP, Python) and 7 UML diagram types, producing 84 observations assessed on 5 automated metrics. Results demonstrate high syntactic validity (mean: 91.5%, with component and deployment diagrams reaching 100%), strong relationship precision (mean: 0.858) and consistent structural quality (mean: 81.7/100, with cross-language variance of 3.1 points). Entity recall averaged 0.313, reflecting deliberate architectural prioritization over exhaustive coverage. A sensitivity analysis (31 to 4,578 IR entities) confirms that quality scores remain stable regardless of scale.
Related papers
- CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System [4.37294181347758]
This paper presents CAPRA, a multi-agent system that analyzes software architecture deliverables to generate template-compliant architectural feedback.<n>Preliminary empirical evaluation on 10 reports shows that CAPRA satisfied 88.8% the evaluated criteria.
arXiv Detail & Related papers (2026-06-17T12:00:21Z) - ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
$textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
arXiv Detail & Related papers (2026-05-11T16:20:51Z) - LLM-based Automated Architecture View Generation: Where Are We Now? [0.0]
We evaluate the ability of LLMs and agentic approaches to generate architecture views from source code.<n>Few-shot prompting reduces clarity failures by 9.2% compared to zero-shot baselines.<n>Custom agentic approach consistently outperforms the general-purpose agent.
arXiv Detail & Related papers (2026-03-22T11:41:37Z) - DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles [5.647839536820347]
We introduce DiscoUQ, a framework that extracts and leverages the structure of inter-agent disagreement to produce well-calibrated confidence estimates.<n>DiscoUQ-LLM achieves an average AUROC of 0.802, outperforming the best baseline.<n>The learned features generalize across benchmarks with near-zero performance degradation.
arXiv Detail & Related papers (2026-03-21T23:24:12Z) - Towards a Science of Scaling Agent Systems [79.64446272302287]
We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
arXiv Detail & Related papers (2025-12-09T06:52:21Z) - ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization [1.580774794371876]
We present ARIAL, a framework that orchestrates specialized tools to achieve both precise answer extraction and reliable spatial grounding.<n>We evaluate ARIAL on four benchmarks (DocVQA, FUNSD, CORD, and SROIE) using both textual accuracy (ANLS) and spatial precision.<n>Our work demonstrates how agentic orchestration of specialized tools can simultaneously improve performance and interpretability.
arXiv Detail & Related papers (2025-11-22T21:09:28Z) - LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
arXiv Detail & Related papers (2025-11-17T23:57:24Z) - MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
arXiv Detail & Related papers (2025-08-13T19:14:48Z) - CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs [16.234259194402163]
We introduce CodeAgents, a prompting framework that codifies multi-agent reasoning and enables structured, token-efficient planning in multi-agent systems.<n>Results show consistent improvements in planning performance, with absolute gains of 3-36 percentage points over natural language prompting baselines.
arXiv Detail & Related papers (2025-07-04T02:20:19Z) - AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios [51.46347732659174]
Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications.<n>AgentIF is the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios.
arXiv Detail & Related papers (2025-05-22T17:31:10Z) - Tool-Augmented Reward Modeling [58.381678612409]
We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments.
Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources.
In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
arXiv Detail & Related papers (2023-10-02T09:47:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.