mlsanityData to 7 Oct 2026

LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems

arXiv 2511.19368 ↗First posted 24 Nov 2025cs.LG cs.NIcited by 8

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the synchronous updates of agent policies. This non stationarity results in unstable training and poor policy con vergence, especially as the number of agents increases. In this paper, we propose RELED, a scalable MARL framework that integrates large language model (LLM)-driven expert demonstrations with autonomous agent exploration. RELED incorporates a Stationarity-Aware Expert Demonstration module, which leverages theoretical non-stationarity bounds to enhance the quality of LLM-generated expert trajectories, thus providing high reward and training-stable samples for each agent. Moreover, a Hybrid Expert-Agent Policy Optimization module adaptively balances each agent's learning from both expert-generated and agent-generated trajectories, accelerating policy convergence and improving generalization. Extensive experiments with real city networks based on OpenStreetMap demonstrate that RELED achieves superior performance compared to state-of-the-art MARL methods.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 62 of its 83 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

62 of 83 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning18 Sep
  2. 2025LLM Collaboration With Multi-Agent Reinforcement Learning6 Aug
  3. 2025LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation2 Jun

Other references · 59

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  4. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  5. 2017Constrained Policy Optimizationcited by 928
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  7. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  8. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  9. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  10. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  11. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  12. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
38 more
  1. 2023Reward Design with Language Modelscited by 257
  2. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 180
  3. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 128
  4. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 125
  5. 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 93
  6. 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunitiescited by 89
  7. 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
  8. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  9. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  10. 2023Split Learning in 6G Edge Networkscited by 68
  11. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  12. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 60
  13. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  14. 2019Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Criticscited by 46
  15. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  16. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  17. 2023Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Roboticscited by 35
  18. 2021Multi-Agent Constrained Policy Optimisationcited by 32
  19. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 30
  20. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaborationcited by 26
  21. 2025LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networkscited by 22
  22. 2023LLaMA Rider: Spurring Large Language Models to Explore the Open Worldcited by 21
  23. 2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
  24. 2020Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learningcited by 19
  25. 2022Asynchronous Actor-Critic for Multi-Agent Reinforcement Learningcited by 16
  26. 2024MERIT: Multimodal Wearable Vital Sign Waveform Monitoringcited by 16
  27. 2024The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Modelscited by 15
  28. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  29. 2024SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensingcited by 14
  30. 2019Edge-Computing-Enabled Smart Cities: A Comprehensive Surveycited by 13
  31. 2025Constructing 4D Radio Map in LEO Satellite Networks with Limited Samplescited by 13
  32. 2024Sums: Sniffing Unknown Multiband Signals under Low Sampling Ratescited by 12
  33. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  34. 2025Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoringcited by 10
  35. 2023LANCAR: Leveraging Language for Context-Aware Robot Locomotion in Unstructured Environmentscited by 9
  36. 2019Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structurecited by 8
  37. 2023Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Controlcited by 8
  38. 2023Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Taskscited by 8

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Expertscited by 11
  2. 2026NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learningcited by 4
  3. 2026Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generationcited by 1
  4. 2026SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compressioncited by 1
  5. 2026Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learningcited by 0
  6. 2026Large Language Model Enhanced Differentiable Trajectory Planning for IoT-Enabled Autonomous Drivingcited by 0
  7. 2026TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectorscited by 0
  8. 2026SeaCausal-FL: Federated Fuzzy Causal Learning for Maritime IoT Fault Diagnosis and Counterfactual Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  2. 2026RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization
  3. 2026LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning
  4. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
  5. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
  6. 2026Rethinking Agentic Reinforcement Learning In Large Language Models
  7. 2026Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
  8. 2026Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems