WORLDWIDE_SanGuai / Research bulletin

[ worldwide.arakne.de ]

世界很大,讀一小點。

SanGuai 的三日研究佈告板。每天更新,讀完就走。

EST. 202672H上架 72 小時
網路與通訊 / 2611.14920

Janus:以單一代理雙重角色統一數位孿生建構與網路編排

Janus: One Agent, Two Roles for Digital Twin Construction and Network Orchestration

作者: Peijun Hou, Yue Zhang, Yi Wei, Nan Cen論文發布: 2026-11-13離架倒數: 15 小時

研究速讀

作者提出 Janus,一個以大型語言模型為基礎的代理框架,將數位孿生建構與網路編排整合進閉環系統。其核心 NetTwin 代理採「一代理、兩角色」範式,同時從部分觀測建構孿生並做任務導向決策,並以規劃、建模、編碼三個模組化角色與統一提示模組強化圖結構推理。

值得留意

  1. 主張以單一代理同時擔任孿生建構與網路決策兩種角色,形成閉環
  2. 架構包含規劃者、建模者、編碼者三個功能角色及統一提示模組
  3. 作者報告在最多 200 節點的無線網路與使用者關聯、SAGIN 路由兩任務上,孿生準確率逾 90%、效能差距在 10.53% 內

閱讀限制

僅依標題與摘要整理,未閱讀全文,無法核驗實驗設定、基線選擇、統計顯著性或開源情形;摘要中的數字均為作者自述。

原始摘要 [EN]

Next-generation wireless networks are increasingly large-scale, heterogeneous, and dynamic, posing significant challenges to network modeling and control. Digital twins offer a promising solution, but existing approaches typically rely on static models and decouple twin construction from network orchestration, limiting adaptability. Meanwhile, large language models (LLMs) provide strong reasoning capabilities but struggle with graph-structured data and are highly sensitive to prompt design, making inference unreliable. In this paper, we propose Janus, an agentic LLM-based framework that unifies digital twin construction and network orchestration within a closed-loop system. At the core of Janus is a novel NetTwin agent, which introduces a new one-agent, two-role paradigm, enabling a single agent to simultaneously construct the digital twin from partial observations while performing task-driven network decision-making. To realize this, we design a modular architecture with three functional roles, including planner, modeler, and coder, along with a newly designed unified prompt module that further enhances graph reasoning robustness. Extensive evaluations on wireless networks with up to 200 nodes and two representative tasks, including user association and SAGIN routing, show that Janus achieves over 90% digital twin accuracy and near-optimal performance with gaps within 10.53%, while maintaining moderate computational overhead. These results demonstrate the effectiveness, scalability, and generalizability of Janus, paving the way for AI-native autonomous wireless network orchestration.

AI 摘要僅根據公開標題與摘要整理;研究結論來自作者,請以原文為準。