AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems

Researchers propose AIVV, a hybrid framework using Large Language Models to automate verification and validation of autonomous systems, replacing manual human oversight. The system uses LLM councils to distinguish between genuine faults and nuisance faults, demonstrated successfully on unmanned underwater vehicle simulations.

• →AIVV framework uses LLMs to automate verification and validation processes that currently require manual human oversight.
• →The system employs a council of specialized LLM agents to collaboratively validate system anomalies and failures.
• →Successfully tested on unmanned underwater vehicle time-series simulations, overcoming limitations of rule-based fault classification.
• →Framework addresses scalability issues in autonomous system oversight across diverse control systems.
• →System generates actionable artifacts like gain-tuning proposals for post-fault system improvements.