Toward Agentic AI: Task-Oriented Communication for Hierarchical Planning of Long-Horizon Tasks

TL;DR

This paper introduces HiTOC, a hierarchical task-oriented communication framework for agentic AI that efficiently transmits only task-relevant information, enabling better performance in complex, long-horizon tasks.

Contribution

The paper develops a novel hierarchical communication framework with a conditional variational information bottleneck for adaptive, minimal information transmission in agentic AI.

Findings

HiTOC outperforms existing schemes in success rate on MAP-THOR benchmark.

The cVIB approach effectively reduces communication overhead.

Hierarchical structure improves handling of long-horizon tasks.

Abstract

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.