# A Task Decomposition and Planning Framework for Efficient LLM Inference in AI-Enabled WiFi-Offload Networks

arXiv: https://arxiv.org/abs/2604.21399 · HTML: https://mlsanity.com/paper/2604.21399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 5 of 5)

- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation](https://mlsanity.com/paper/2501.05647/) (2025)
- [HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference](https://mlsanity.com/paper/2512.22137/) (2025)

## Built on by (most cited first, 1 of 1)

- [IEEE 802.11bx - WLAN Intelligent Networking (WIN): Toward an AI-Ready Wi-Fi 9](https://mlsanity.com/paper/2610.07900/) (2026)

## Abstract (arXiv)

AI WiFi offload is emerging as a promising approach for providing large language model (LLM) services to resource-constrained wireless devices. However, unlike conventional edge computing, LLM inference over WiFi must jointly address heterogeneous model capabilities, wireless contention, uncertain task complexity, and semantic correlation among reasoning tasks. In this paper, we investigate LLM inference offloading in a multi-user multi-edge WiFi network, where each task can be executed locally, directly offloaded to a nearby edge access point (AP), or decomposed into multiple subtasks for collaborative execution across local and edge nodes. To this end, we propose a user-edge collaborative framework with an LLM-based planner that not only performs task decomposition but also infers subtask difficulty and expected output token length, enabling more accurate estimation of execution quality and latency on heterogeneous nodes. Based on these estimates, we further design a decomposition-aware scheduling strategy that jointly optimizes subtask assignment, execution, and aggregation under communication, queuing, and computation constraints. Simulation results show that the proposed framework achieves a better latency-accuracy tradeoff than local-only and nearest-edge baselines, reducing the average latency by 20% and improving the overall reward by 80%. Moreover, the distilled lightweight planner approaches the performance of the large teacher model while remaining more suitable for practical edge deployment.