mlsanityData to 14 Oct 2026

LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts

arXiv 2608.14956 ↗First posted 15 Aug 2026cs.LG cs.LOcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

The development of models demands sound modeling and simulation knowledge as well as domain knowledge. Every model should accurately represent a system's dynamics and be verifiable. Toward this objective, this research introduces an agentic PDEVS-LLM framework to assist human modelers in generating and verifying PDEVS statecharts for behavior modeling of atomic Parallel Discrete Event System Specification (PDEVS) models. The framework supports (re)generating plausible facts from a system description prompt using the agentic LLM used for generating plausible facts. Inconsistencies in plausible facts lead to incorrect PDEVS statecharts having logical structure and behavioral inaccuracies. A controlled-correction mechanism is developed to verify the logical consistency of the plausible facts. The agentic LLM is used to generate key behavioral conditions from the system description prompt. The plausible facts are then verified against the behavioral conditions using propositional logic entailment for a finite number of times. The verification results enable the generation of modification prompts that can reduce errors in generated plausible facts, resulting in more accurate PDEVS statecharts. To verify a statechart's logical correctness, its Timed Automata counterpart is manually created and verified for deadlock and reachability properties. The human modeler may regenerate plausible facts and PDEVS statecharts iteratively and incrementally. A basic correctness metric is introduced to quantify the completeness and accuracy of the expected behavioral traits of the PDEVS statechart models. A collection of example systems with varying levels of complexity is developed to demonstrate the capabilities and limitations of LLMs. The evaluation of the proposed verification mechanism shows a substantial improvement in the logical consistency of generated statecharts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 8 of its 29 references that are in the map. First posted on arXiv 15 Aug 2026.

Builds on

8 of 29 references.

References · 8

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Language Models can Solve Computer Taskscited by 372
  5. 2023A Bibliometric Review of Large Language Models Research from 2017 to 2023cited by 57
  6. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
  7. 2023GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Taskscited by 14
  8. 2021SLGPT: Using Transfer Learning to Directly Generate Simulink Model Files and Find Bugs in the Simulink Toolchaincited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework
  2. 2026Event-B Agent: Towards LLM Agent for Formal Model Synthesis and Repair
  3. 2025An Approach to Checking Correctness for Agentic Systems
  4. 2026Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
  5. 2024Specifications: The missing link to making the development of LLM systems an engineering discipline
  6. 2025Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications
  7. 2026Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
  8. 2025SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine