arXiv cs.MA· Mahmoud S. Mayaleh, Fetia Bannour, Nour-El-Houda Yellas·· 11 小时前AI 评分20
ORION：面向 RL 多域 6G 网络切片放置的结果驱动 LLM 顾问
ORION: An Outcome-Driven LLM Advisor for RL-Based Multi-Domain 6G Slice Placement
AI 导读
ORION 是一个分层编排器，用两个 LLM 智能体将服务意图转为结构化请求并生成抽象放置方案，再由协作式多智能体 RL 协调器选择跨域划分。其核心是结果驱动的情景记忆，记录每次尝试的网络状况、方案与验证后的可行性结果，把成功与失败反馈给规划器。
正文 · 原文
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.
| Comments: | Accepted at IEEE MobiWac 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2610.41563 [cs.LG] |
| (or arXiv:2610.41563v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41563 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mahmoud S. Mayaleh [view email]
[v1]
Fri, 30 Oct 2026 10:58:06 UTC (83 KB)
来源：arXiv cs.MA · arxiv.org