Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN

arXiv:2604.09682v1 Announce Type: cross Abstract: Autonomous network management in Open Radio Access Networks requires intelligent decision making across conflicting objectives, yet existing LLM based multi agent systems employ homogeneous strategies and lack systematic predeployment validation. We introduce a persona driven multi agent framework where configurable behavioral personas structured specifications encoding optimization priorities, risk tolerance, and decision making style influence five specialized agents (planning, coordination, resource allocation, code generation, analysis). To enable rigorous validation, we develop a three dimensional evaluation framework grounded in decision theory, measuring normative compliance (optimality adherence), prescriptive alignment (behavioral guideline consistency), and behavioral dynamics (emergent system properties). We evaluate 486 persona configurations across two ORAN optimization challenges (energy efficient resource allocation and network load balancing). Results demonstrate that persona agent alignment significantly impacts both individual performance (14.3 percent) and emergent multi agent coordination, with retrieval architecture (GraphRAG vs. RAG) fundamentally constraining customization effectiveness. Single agent persona modifications propagate system wide through cascading effects, with certain combinations exhibiting detectable fundamental incompatibilities. Our framework provides systematic validation mechanisms for deploying LLM based automation in mission critical telecommunications infrastructure.

Related

• OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
• MOSAIC: Multi-Domain Orthogonal Session Adaptive Intent Capture for Prescient Recommendations
• LLM-based Realistic Safety-Critical Driving Video Generation
• AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power
• Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation
• Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

Source: arXiv cs.AI | 2026-04-14