paper-with-me

Papers

AgentGuard: Runtime Verification of AI Agents

2025-09-28 · Roham Koohestani arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.23864

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration

2025-02-13 · Jizhou Chen, Samuel Lee Cong

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more conseque…

AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior

2026-01-15 · Nadya Abaev, Denis Klimov, Gerard Levinov, David Mimran 외 arxiv

Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions a…

RV4JaCa -- Runtime Verification for Multi-Agent Systems

2022-07-20 · Debora C. Engelmann, Angelo Ferrando, Alison R. Panisson, Davide Ancona 외

This paper presents a Runtime Verification (RV) approach for Multi-Agent Systems (MAS) using the JaCaMo framework. Our objective is to bring a layer of security to the MAS. This layer is capable of controlling events dur…

Decision Making

Zero-Trust Runtime Verification for Agentic Payment Protocols: Mitigating Replay and Context-Binding Failures in AP2

2026-02-06 · Qianlong Lan, Anuj Kaul, Shaun Jones, Stephanie Westrum arxiv

The deployment of autonomous AI agents capable of executing commercial transactions has motivated the adoption of mandate-based payment authorization protocols, including the Universal Commerce Protocol (UCP) and the Age…

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

2026-05-13 · Hailin Zhong, Shengxin Zhu arxiv

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability.…

Code Generation