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

• URL: http://arxiv.org/abs/2604.07148v1
• Date: Wed, 08 Apr 2026 14:38:48 GMT
• Title: Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing
• Abstract summary: We propose COMLLM, a generative framework that enables foresighted decision-making in MEC systems.<n> COMLLM achieves near-optimal latency and improved load-balancing fairness. Notably, it exhibits zero-shot scalability, allowing a model trained on smallscale networks to generalize to larger, unseen topologies without retraining.
• Score: 15.718757401948304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services [13.04369901641143]
  Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference.<n>We develop a cross-slot inference model that captures transmission, prefill, redistribution-level decoding, and key-value cache evolution for each diverse request.<n>We propose the LYREO approach that transforms the long-term load-balancing constraint via Lyapunov optimization and employs reward with sequencebased return prediction.
  arXiv  Detail & Related papers  (2026-09-15T13:50:54Z)
• Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling [11.212756680882444]
  We introduce RACE-Sched, an agent-based framework that decouples policy execution from logical reasoning via a dual-stream architecture.<n>This approach harmonizes real-time constraints with long-horizon reasoning to achieve superior solution quality and robust adaptation to dynamic events.
  arXiv  Detail & Related papers  (2026-05-28T02:26:18Z)
• Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach [2.7564583149786075]
  Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers.<n>In this paper, we propose a Federated Meta Deep Reinforcement Learning framework with GAT-Seq2Seq modeling (FedMAGS) for heterogeneous task offloading in VEC systems.
  arXiv  Detail & Related papers  (2026-05-18T14:08:51Z)
• SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval [74.1918709002557]
  We introduce textbfSGA-MCTS, a framework that casts LLM planning as non-parametric retrieval.<n>Online, a retrieval-augmented agent employs a hybrid symbolic-semantic mechanism to fetch relevant State-Goal-Action atoms.<n>By effectively amortizing the heavy computational cost of search, SGA-MCTS achieves System 2 reasoning depth at System 1 inference speeds, rendering autonomous planning both scalable and real-time feasible.
  arXiv  Detail & Related papers  (2026-04-16T07:22:36Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning [67.78566256784404]
  Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting.<n>Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure.<n>We propose a textbfContinual textbfGUI textbfLearning framework that balances efficiency and skill retention.
  arXiv  Detail & Related papers  (2026-03-03T13:02:20Z)
• Reinforcement learning with timed constraints for robotics motion planning [0.5436465344481877]
  This paper presents a unified automata-based framework for synthesizing policies in both Markov Decision Processes (MDPs) and Partially Observable Markov Decision Processes (POMDPs)<n>A simple yet expressive reward structure enforces temporal correctness while allowing additional performance objectives.<n>Results demonstrate that the proposed framework consistently learns policies that satisfy strict time-bounded requirements under transitions, scales to larger state spaces, and remains effective in partially observable environments.
  arXiv  Detail & Related papers  (2025-12-31T19:43:44Z)
• Adaptive Approach to Enhance Machine Learning Scheduling Algorithms During Runtime Using Reinforcement Learning in Metascheduling Applications [0.0]
  We propose an adaptive online learning unit integrated within the metascheduler to enhance performance in real-time.<n>In the online mode, Reinforcement Learning plays a pivotal role by continuously exploring and discovering new scheduling solutions.<n>Several RL models were implemented within the online learning unit, each designed to address specific challenges in scheduling.
  arXiv  Detail & Related papers  (2025-09-24T19:46:22Z)
• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services [14.408050197587654]
  Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services.<n> deploying DNN models on resource-constrained edge devices introduces additional challenges, including limited/storage resources, dynamic service demands, and heightened privacy risks.<n>This paper presents a novel privacy-aware optimization framework that jointly addresses DNN model deployment, user-server association, and model partitioning.
  arXiv  Detail & Related papers  (2025-02-22T05:27:24Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks [44.37047471448793]
  In this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL) We propose an innovative PSL framework, namely, efficient parallel split learning (EPSL) to accelerate model training. We show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy.
  arXiv  Detail & Related papers  (2023-03-26T16:09:48Z)
• Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning [11.007816552466952]
  This paper focuses on the problem of scheduling inference queries on Deep Neural Networks in edge networks at short timescales. By means of simulations, we analyze several policies in the realistic network settings and workloads of a large ISP. We design ASET, a Reinforcement Learning based scheduling algorithm able to adapt its decisions according to the system conditions.
  arXiv  Detail & Related papers  (2023-01-31T13:23:34Z)
• Architecture Aware Latency Constrained Sparse Neural Networks [35.50683537052815]
  In this paper, we design an architecture aware latency constrained sparse framework to prune and accelerate CNN models. We also propose a novel sparse convolution algorithm for efficient computation. Our system-algorithm co-design framework can achieve much better frontier among network accuracy and latency on resource-constrained mobile devices.
  arXiv  Detail & Related papers  (2021-09-01T03:41:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.