Toward Agentic AI: Task-Oriented Communication for Hierarchical Planning of Long-Horizon Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915795527794688 |
|---|---|
| author | Huang, Sin-Yu Wang, Lele Wong, Vincent W. S. |
| author_facet | Huang, Sin-Yu Wang, Lele Wong, Vincent W. S. |
| contents | Agentic artificial intelligence (AI) is an AI paradigm that can perceive the environment, reason over observations, and execute actions to achieve specific goals. Task-oriented communication supports agentic AI by transmitting only the task-related information instead of full raw data in order to reduce the bandwidth requirement. In real-world scenarios, AI agents often need to perform a sequence of actions to complete complex tasks. Completing these long-horizon tasks requires a hierarchical agentic AI architecture, where a high-level planner module decomposes a task into subtasks, and a low-level actor module executes each subtask sequentially. Since each subtask has a distinct goal, the existing task-oriented communication schemes are not designed to handle different goals for different subtasks. To address this challenge, in this paper, we develop a hierarchical task-oriented communication (HiTOC) framework. We consider a system with an edge server and a robot as an edge device. The high-level planner and low-level actor modules reside on the edge server. The robot transmits only the environmental observation that is relevant to the current subtask to the edge server. We propose a conditional variational information bottleneck (cVIB) approach to train the HiTOC framework to adaptively transmit minimal information required for each subtask. Simulations conducted on the AI2-THOR platform demonstrate that the proposed HiTOC framework outperforms three state-of-the-art schemes in terms of the success rate on MAP-THOR benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13685 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Agentic AI: Task-Oriented Communication for Hierarchical Planning of Long-Horizon Tasks Huang, Sin-Yu Wang, Lele Wong, Vincent W. S. Image and Video Processing Agentic artificial intelligence (AI) is an AI paradigm that can perceive the environment, reason over observations, and execute actions to achieve specific goals. Task-oriented communication supports agentic AI by transmitting only the task-related information instead of full raw data in order to reduce the bandwidth requirement. In real-world scenarios, AI agents often need to perform a sequence of actions to complete complex tasks. Completing these long-horizon tasks requires a hierarchical agentic AI architecture, where a high-level planner module decomposes a task into subtasks, and a low-level actor module executes each subtask sequentially. Since each subtask has a distinct goal, the existing task-oriented communication schemes are not designed to handle different goals for different subtasks. To address this challenge, in this paper, we develop a hierarchical task-oriented communication (HiTOC) framework. We consider a system with an edge server and a robot as an edge device. The high-level planner and low-level actor modules reside on the edge server. The robot transmits only the environmental observation that is relevant to the current subtask to the edge server. We propose a conditional variational information bottleneck (cVIB) approach to train the HiTOC framework to adaptively transmit minimal information required for each subtask. Simulations conducted on the AI2-THOR platform demonstrate that the proposed HiTOC framework outperforms three state-of-the-art schemes in terms of the success rate on MAP-THOR benchmark. |
| title | Toward Agentic AI: Task-Oriented Communication for Hierarchical Planning of Long-Horizon Tasks |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2601.13685 |