Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems

cs.AI

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: 11 pages, 3 figures

Code: https://github.com/DLR-RM/stable-baselines3

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Continuous control with deep reinforcement learning
• Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
• Towards Deep Learning Models Resistant to Adversarial Attacks

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems