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

arXiv: https://arxiv.org/abs/2604.09682 · HTML: https://mlsanity.com/paper/2604.09682/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [A Persona-Based Neural Conversation Model](https://mlsanity.com/paper/1603.06155/) (2016)
- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [Large Language Model Enhanced Multi-Agent Systems for 6G Communications](https://mlsanity.com/paper/2312.07850/) (2023)
- [Intelligence and Learning in O-RAN for Data-driven NextG Cellular Networks](https://mlsanity.com/paper/2012.01263/) (2020)
- [Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligence](https://mlsanity.com/paper/2307.02757/) (2023)
- [The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms](https://mlsanity.com/paper/2307.07319/) (2023)
- [Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level](https://mlsanity.com/paper/2404.05337/) (2024)
- [CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation](https://mlsanity.com/paper/2401.06786/) (2023)
- [Generative AI on the Edge: Architecture and Performance Evaluation](https://mlsanity.com/paper/2411.17712/) (2024)
- [Next Steps in LLM-Supported Java Verification](https://mlsanity.com/paper/2502.01573/) (2025)
- [Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach](https://mlsanity.com/paper/2312.17353/) (2023)
- [GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective](https://mlsanity.com/paper/2507.09495/) (2025)
- [Safety and Risk Pathways in Cooperative Generative Multi-Agent Systems: A Telecom Perspective](https://mlsanity.com/paper/2511.17730/) (2025)

## Abstract (arXiv)

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.