{"ID":2864323,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23864","arxiv_id":"2509.23864","title":"AgentGuard: Runtime Verification of AI Agents","abstract":"The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards probabilistic guarantees where the question is no longer if a system will fail, but the probability of its failure within given constraints. This paper presents AgentGuard, a framework for runtime verification of Agentic AI systems that provides continuous, quantitative assurance through a new paradigm called Dynamic Probabilistic Assurance. AgentGuard operates as an inspection layer that observes an agent's raw I/O and abstracts it into formal events corresponding to transitions in a state model. It then uses online learning to dynamically build and update a Markov Decision Process (MDP) that formally models the agent's emergent behavior. Using probabilistic model checking, the framework then verifies quantitative properties in real-time.","short_abstract":"The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards probabilistic guarantees where the question is no longer if a system will fail,...","url_abs":"https://arxiv.org/abs/2509.23864","url_pdf":"https://arxiv.org/pdf/2509.23864v1","authors":"[\"Roham Koohestani\"]","published":"2025-09-28T13:08:50Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.SE\"]","methods":"[]","has_code":false}