# Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing

arXiv: https://arxiv.org/abs/2604.07148 · HTML: https://mlsanity.com/paper/2604.07148/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 9 of 9)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Mobile Edge Computing: A Survey on Architecture and Computation Offloading](https://mlsanity.com/paper/1702.05309/) (2017)
- [Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing Systems](https://mlsanity.com/paper/2005.02459/) (2020)
- [Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading](https://mlsanity.com/paper/2501.14205/) (2025)
- [Generative AI as a Service in 6G Edge-Cloud: Generation Task Offloading by In-context Learning](https://mlsanity.com/paper/2408.02549/) (2024)
- [Multi-objective Deep Reinforcement Learning for Mobile Edge Computing](https://mlsanity.com/paper/2307.14346/) (2023)
- [Generalizable Pareto-Optimal Offloading with Reinforcement Learning in Mobile Edge Computing](https://mlsanity.com/paper/2509.10474/) (2025)
- [Egret: Reinforcement Mechanism for Sequential Computation Offloading in Edge Computing](https://mlsanity.com/paper/2404.09285/) (2024)
- [Minimizing AoI in Mobile Edge Computing: Nested Index Policy with Preemptive and Non-preemptive Structure](https://mlsanity.com/paper/2508.20564/) (2025)

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

- [Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing](https://mlsanity.com/paper/2608.12371/) (2026)

## Abstract (arXiv)

Emerging computation-intensive applications impose stringent latency requirements on resource-constrained mobile devices. Mobile Edge Computing (MEC) addresses this challenge through task offloading. However, designing effective policies remains difficult due to dynamic task arrivals, time-varying channels, and the spatio-temporal coupling of server queues. Conventional heuristics lack adaptability, while Deep Reinforcement Learning (DRL) suffers from limited generalization and architectural rigidity, requiring retraining when network topology changes. Although Large Language Models (LLMs) offer semantic reasoning capabilities, standard Supervised Fine-Tuning (SFT) yields myopic policies that greedily minimize immediate latency without accounting for long-term system evolution. To address these limitations, we propose COMLLM, a generative framework that enables foresighted decision-making in MEC systems. COMLLM integrates Group Relative Policy Optimization (GRPO) with a Look-Ahead Collaborative Simulation (LACS) mechanism, which performs multi-step Monte Carlo rollouts while jointly modeling server queue dynamics. By incorporating these rollouts into the reward design, the framework captures the long-term impact of current decisions on future system states. Experimental results demonstrate that COMLLM achieves near-optimal latency and improved load-balancing fairness. Notably, it exhibits zero-shot topological scalability, allowing a model trained on small-scale networks to generalize to larger, unseen topologies without retraining, outperforming SFT, DRL, and heuristic baselines.