Formal Runtime Verification for Tool-Using LLM Agents: An Offline Same-Benchmark Study on AgentDojo and STAC

arXiv:2610.09793 · cs.CR · Submitted 2026-10-07 · Read on arXiv

cs.CR

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/nikos-kekatos/formal-rv-tool-usingllm-agents

Terminology

• Trace — 63× in this paper · explained in 2 episodes
• Benchmark — 43× in this paper · explained in 2 episodes
• Provenance — 42× in this paper · explained in 3 episodes
• Verification — 23× in this paper · explained in 2 episodes
• Runtime Verification — 18× in this paper
• Ablation — 8× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Cyber Security and Resilience — 3× in this paper
• Adaptation — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Formal Methods — 2× in this paper · explained in 3 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Agentic Components — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
• SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
• STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
• Progent: Securing AI Agents with Privilege Control
• GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
• Agent-SafetyBench: Evaluating the Safety of LLM Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs