ModelWisdom: An Integrated Toolkit for TLA+ Model Visualization, Digest and Repair

2026-02-12

AI Summary

This work proposes the first interactive debugging environment that integrates large language models (LLMs) with TLA+ model checking to address the poor interpretability and limited interactivity commonly encountered in traditional approaches, which often produce opaque counterexamples, unwieldy state graphs, and difficult-to-diagnose violations. By combining structured visualizations, collapsible state graphs, violation highlighting, traceable code links, and LLM-generated semantic summaries, the framework transforms raw model-checking outputs into an actionable, user-guided debugging workflow. This approach substantially enhances the comprehensibility of complex specifications and significantly improves debugging efficiency, thereby reducing the verification and repair costs associated with non-trivial systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Model checking in TLA+ provides strong correctness guarantees, yet practitioners continue to face significant challenges in interpreting counterexamples, understanding large state-transition graphs, and repairing faulty models. These difficulties stem from the limited explainability of raw model-checker output and the substantial manual effort required to trace violations back to source specifications. Although the TLA+ Toolbox includes a state diagram viewer, it offers only a static, fully expanded graph without folding, color highlighting, or semantic explanations, which limits its scalability and interpretability. We present ModelWisdom, an interactive environment that uses visualization and large language models to make TLA+ model checking more interpretable and actionable. ModelWisdom offers: (i) Model Visualization, with colorized violation highlighting, click-through links from transitions to TLA+ code, and mapping between violating states and broken properties; (ii) Graph Optimization, including tree-based structuring and node/edge folding to manage large models; (iii) Model Digest, which summarizes and explains subgraphs via large language models (LLMs) and performs preprocessing and partial explanations; and (iv) Model Repair, which extracts error information and supports iterative debugging. Together, these capabilities turn raw model-checker output into an interactive, explainable workflow, improving understanding and reducing debugging effort for nontrivial TLA+ specifications. The website to ModelWisdom is available: https://model-wisdom.pages.dev. A demonstrative video can be found at https://www.youtube.com/watch?v=plyZo30VShA.

Problem

• TLA+
• model checking
• counterexample interpretation
• state-transition graph
• model repair

Innovation

• TLA+
• model checking
• visualization
• large language models
• debugging