ORION: An Outcome-Driven LLM Advisor for RL-Based Multi-Domain 6G Slice Placement
cs.LG, cs.AI, cs.MA, cs.NI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted at IEEE MobiWac 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Deploying 6G network slices across administrative domains requires an online decision for each arriving request: which domain hosts each virtual network function…
Terminology
Abstract
Deploying 6G network slices across administrative domains requires an online decision for each arriving request: which domain hosts each virtual network function, how traffic crosses domain boundaries, and whether the slice is admitted. This joint decision problem is NP-hard under continuous arrivals. Experiments on a parametrized family of multi-domain topologies show that no fixed planning strategy dominates across all regimes: the performance ranking reverses between topology classes, and feasible placements exist for most rejected requests but remain undiscovered. These findings identify the plan layer as the decisive performance lever. We introduce ORION, a hierarchical orchestrator in which two LLM agents translate service intents into structured requests and generate abstract placement plans. A cooperative multi-agent RL coordinator selects the cross-domain partition, treating the plan as a persistent soft prior, while per-domain agents place the functions. ORION main contribution lies at the plan layer: an outcome-driven episodic memory that records, for each completed attempt, the network-condition profile, the proposed plan, and its verified feasibility outcome. The memory feeds verified successes and labelled failures back to the planner, thereby closing the adaptation loop using deployment feasibility rather than a scalar reward assigned to the planner's own proposals. To isolate the effect of the plan quality, we evaluate the planner on held-out topology families while keeping the downstream selection and execution mechanisms fixed. Under this controlled setting, the proposed memory improves admission by 4.6 -- 11.5 percentage points over the same planner without memory, while importance-based retention accounts for most of the improvement over a first-in-first-out store.
Sources
- Large Language Models meet Network Slicing Management and Orchestration
- How Can LLM Guide RL? A Value-Based Approach
- Efficient Reinforcement Learning with Large Language Model Priors
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- ORAN-GUIDE: RAG-Driven Prompt Learning for LLM-Augmented Reinforcement Learning in O-RAN Network Slicing
- Prompt-Tuned LLM-Augmented DRL for Dynamic O-RAN Network Slicing
- LLM-Empowered Agentic AI for QoE-Aware Network Slicing Management in Industrial IoT
- A-MEM: Agentic Memory for LLM Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
Related papers
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning
- Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine