arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.41563cs.LGcs.AIcs.MAcs.NI
收藏

ORION:面向基于强化学习的多域6G切片部署的结果驱动型大语言模型(LLM)顾问

ORION: An Outcome-Driven LLM Advisor for RL-Based Multi-Domain 6G Slice Placement

ensIIE, SAMOVAR(南巴黎电信学院国际工业工程学院、萨莫瓦尔实验室);LIX, École polytechnique, Institut Polytechnique de Paris(利克实验室、巴黎综合理工学院、巴黎理工学院)

Mahmoud S. Mayaleh, Fetia Bannour, Nour-El-Houda Yellas

AI总结:

针对多域6G切片部署的NP难在线决策问题,提出结果驱动型LLM顾问ORION,其规划层的情景记忆可提升请求接纳率4.6-11.5个百分点。

摘要:

在跨管理域部署6G网络切片时,需对每个到达的请求做出在线决策:哪个域托管每个虚拟网络功能、流量如何跨域传输,以及是否接纳该切片。在请求持续到达的情况下,这一联合决策问题是NP难问题。对参数化多域拓扑族的实验表明,没有固定规划策略能在所有场景中占优:性能排名会在不同拓扑类之间反转,且大多数被拒绝的请求存在可行部署方案但未被发现。这些发现确定了规划层是决定性的性能杠杆。我们引入ORION,这是一个分层编排器,其中两个LLM智能体将服务意图转换为结构化请求并生成抽象部署规划。一个协作式多智能体强化学习(RL)协调器选择跨域分区,将规划视为持久软先验,而各域内智能体则部署功能。ORION的主要贡献在于规划层:一种结果驱动型情景记忆,它为每个完成的尝试记录网络状况概况、提出的规划及其验证后的可行性结果。该记忆将验证后的成功案例和标记的失败案例反馈给规划器,从而利用部署可行性而非分配给规划器自身提案的标量奖励来关闭适应循环。为隔离规划质量的影响,我们在保留的拓扑族上评估规划器,同时保持下游选择和执行机制固定。在该受控设置下,与无记忆的相同规划器相比,所提出的记忆将接纳率提高了4.6至11.5个百分点,而基于重要性的保留机制是其优于先进先出存储的主要改进来源。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑