# LLM-Mediated Guidance of MARL Systems

arXiv: https://arxiv.org/abs/2503.13553 · HTML: https://mlsanity.com/paper/2503.13553/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Large Language Models for Robotics: Opportunities, Challenges, and Perspectives](https://mlsanity.com/paper/2401.04334/) (2024)
- [LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions](https://mlsanity.com/paper/2405.11106/) (2024)
- [SayTap: Language to Quadrupedal Locomotion](https://mlsanity.com/paper/2306.07580/) (2023)
- [A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment](https://mlsanity.com/paper/2312.01058/) (2023)
- [Interactive Teaching Algorithms for Inverse Reinforcement Learning](https://mlsanity.com/paper/1905.11867/) (2019)
- [Learning to cooperate: Emergent communication in multi-agent navigation](https://mlsanity.com/paper/2004.01097/) (2020)
- [Steering No-Regret Learners to a Desired Equilibrium](https://mlsanity.com/paper/2306.05221/) (2023)
- [HIVEX: A High-Impact Environment Suite for Multi-Agent Research (extended version)](https://mlsanity.com/paper/2501.04180/) (2025)

## Built on by (most cited first, 3 of 3)

- [Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning](https://mlsanity.com/paper/2603.07972/) (2026)
- [RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms](https://mlsanity.com/paper/2507.01378/) (2025)
- [LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.29293/) (2026)

## Abstract (arXiv)

In complex multi-agent environments, achieving efficient learning and desirable behaviours is a significant challenge for Multi-Agent Reinforcement Learning (MARL) systems. This work explores the potential of combining MARL with Large Language Model (LLM)-mediated interventions to guide agents toward more desirable behaviours. Specifically, we investigate how LLMs can be used to interpret and facilitate interventions that shape the learning trajectories of multiple agents. We experimented with two types of interventions, referred to as controllers: a Natural Language (NL) Controller and a Rule-Based (RB) Controller. The RB Controller showed a stronger impact than the NL Controller, which uses a small (7B/8B) LLM to simulate human-like interventions. Our findings indicate that agents particularly benefit from early interventions, leading to more efficient training and higher performance. Both intervention types outperform the baseline without interventions, highlighting the potential of LLM-mediated guidance to accelerate training and enhance MARL performance in challenging environments.