Towards Security-Auditable LLM Agents: A Unified Graph Representation

arXiv:2605.06812 · cs.AI · Submitted 2026-05-07 · Read on arXiv

cs.AI

Submitted: 2026-05-07

Updated: 2026-10-14

Code: https://github.com/openclaw/openclaw

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

Terminology

• Agentic System — 2× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Semantic Gap — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
• AgentOps: Enabling Observability of LLM Agents
• Agent-Sentry: Bounding LLM Agents via Execution Provenance
• Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
• TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
• Agents of Chaos
• AIBoMGen: Generating an AI Bill of Materials for Secure, Transparent, and Compliant Model Training
• RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

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