Agoran: An Agentic Open Marketplace for 6G RAN Automation

2025-08-05

AI Summary

6G network slicing must reconcile conflicting objectives across multiple service providers, yet existing controllers are rigid, policy-driven, and lack business-context awareness. To address this, we propose Agoran—an intelligent, open market framework featuring a novel tripartite AI agent architecture inspired by the “legislative–executive–judicial” separation of powers. Agoran integrates LLM-augmented retrieval, a vector database for real-time environmental sensing, and a rule-based trust scoring mechanism to enable dynamic resource negotiation and real-time arbitration of malicious behavior. The system unifies a retrieval-augmented LLM, a multi-objective optimizer, a rule engine, and a lightweight fine-tuned 1B-parameter Llama model (requiring only 6 GiB memory and 1.3 s inference latency). Evaluated on a live 5G testbed, Agoran achieves a 37% eMBB throughput gain, 73% reduction in URLLC end-to-end latency, and 8.3% lower PRB consumption, with decision quality reaching ~80% of GPT-4.1’s.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Algorithm Configuration

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Next-generation mobile networks must reconcile the often-conflicting goals of multiple service owners. However, today's network slice controllers remain rigid, policy-bound, and unaware of the business context. We introduce Agoran Service and Resource Broker (SRB), an agentic marketplace that brings stakeholders directly into the operational loop. Inspired by the ancient Greek agora, Agoran distributes authority across three autonomous AI branches: a Legislative branch that answers compliance queries using retrieval-augmented Large Language Models (LLMs); an Executive branch that maintains real-time situational awareness through a watcher-updated vector database; and a Judicial branch that evaluates each agent message with a rule-based Trust Score, while arbitrating LLMs detect malicious behavior and apply real-time incentives to restore trust. Stakeholder-side Negotiation Agents and the SRB-side Mediator Agent negotiate feasible, Pareto-optimal offers produced by a multi-objective optimizer, reaching a consensus intent in a single round, which is then deployed to Open and AI RAN controllers. Deployed on a private 5G testbed and evaluated with realistic traces of vehicle mobility, Agoran achieved significant gains: (i) a 37% increase in throughput of eMBB slices, (ii) a 73% reduction in latency of URLLC slices, and concurrently (iii) an end-to-end 8.3% saving in PRB usage compared to a static baseline. An 1B-parameter Llama model, fine-tuned for five minutes on 100 GPT-4 dialogues, recovers approximately 80% of GPT-4.1's decision quality, while operating within 6 GiB of memory and converging in only 1.3 seconds. These results establish Agoran as a concrete, standards-aligned path toward ultra-flexible, stakeholder-centric 6G networks. A live demo is presented https://www.youtube.com/watch?v=h7vEyMu2f5w&ab_channel=BubbleRAN.

Problem

• Reconcile conflicting goals of multiple service owners in 6G networks
• Overcome rigidity and lack of business awareness in current network slice controllers
• Enable stakeholder-centric negotiation for Pareto-optimal resource allocation

Innovation

• Agentic marketplace with autonomous AI branches
• Multi-objective optimizer for Pareto-optimal offers
• Fine-tuned Llama model for efficient decision-making