ARTFEED — Contemporary Art Intelligence

GuardAD: Markovian Logic for Safer Autonomous Driving MLLMs

ai-technology · 2026-05-12

Researchers propose GuardAD, a model-agnostic safeguard for multimodal large language models (MLLMs) in autonomous driving. It uses Neuro-Symbolic Logic Formalization and n-th order Markovian Logic Induction to represent safety as an evolving logical state, enabling detection of emerging hazards beyond single-step observations. This addresses limitations of static safeguards in dynamic traffic environments.

Key facts

  • GuardAD is a model-agnostic safeguard for MLLMs in autonomous driving.
  • It uses Neuro-Symbolic Logic Formalization to represent safety predicates.
  • Safety is formulated as an evolving Markovian logical state.
  • n-th order Markovian Logic Induction enables inference of latent hazards.
  • The approach addresses limitations of static safeguard mechanisms.
  • The paper is published on arXiv with ID 2605.10386.
  • The method is designed for dynamic driving environments.
  • It does not simply veto unsafe actions but reasons over evolving interactions.

Entities

Institutions

  • arXiv

Sources