mlsanityData to 14 Oct 2026

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation

arXiv 2506.01538 ↗First posted 2 Jun 2025cs.RO cs.AIcited by 13

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

Abstract (arXiv)

Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in single-robot settings, but their application in multi-robot systems remains largely unexplored. This paper introduces a novel LLM-Aided MARL (LAMARL) approach, which integrates MARL with LLMs, significantly enhancing sample efficiency without requiring manual design. LAMARL consists of two modules: the first module leverages LLMs to fully automate the generation of prior policy and reward functions. The second module is MARL, which uses the generated functions to guide robot policy training effectively. On a shape assembly benchmark, both simulation and real-world experiments demonstrate the unique advantages of LAMARL. Ablation studies show that the prior policy improves sample efficiency by an average of 185.9% and enhances task completion, while structured prompts based on Chain-of-Thought (CoT) and basic APIs improve LLM output success rates by 28.5%-67.5%. Videos and code are available at https://windylab.github.io/LAMARL/

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 23 of its 38 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

23 of 38 references.

References · 23

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023A Survey of Large Language Modelscited by 2,576
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  7. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  8. 2017Count-Based Exploration with Neural Density Modelscited by 257
  9. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
  10. 2023Text2Reward: Reward Shaping with Language Models for Reinforcement Learningcited by 160
  11. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  12. 2024To Believe or Not to Believe Your LLMcited by 120
11 more
  1. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 106
  2. 2018On Learning Intrinsic Rewards for Policy Gradient Methodscited by 102
  3. 2020Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferencescited by 71
  4. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 61
  5. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  6. 2021Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrianscited by 28
  7. 2023Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learningcited by 12
  8. 2024RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Modelscited by 12
  9. 2024Challenges Faced by Large Language Models in Solving Multi-Agent Flockingcited by 7
  10. 2024Counterfactual rewards promote collective transport using individually controlled swarm microrobotscited by 4
  11. 2018Bearing Rigidity Theory and its Applications for Control and Estimation of Network Systems: Life Beyond Distance Rigiditycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 10.

13 papers.

Sort:

By area:

  1. 2026Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judgecited by 18
  2. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  3. 2025Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approachcited by 12
  4. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  5. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  6. 2026SAGE: Multi-Agent Self-Evolution for LLM Reasoningcited by 6
  7. 2026Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learningcited by 2
  8. 2026Guiding Vector Field Generation via Score-based Diffusion Modelcited by 1
  9. 2026LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learningcited by 0
  10. 2026Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learningcited by 0
  11. 2026EFLUX: Elastic Multi-Robot Formation Navigation and Adaptation with Agentic LLMscited by 0
  12. 2026A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturingcited by 0
1 more
  1. 2026A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning
  2. 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy
  3. 2025LLM-Mediated Guidance of MARL Systems
  4. 2026Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
  5. 2025Language-Driven Coordination and Learning in Multi-Agent Simulation Environments
  6. 2024MARLIN: Multi-Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiation
  7. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
  8. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions