# LLM Collaboration With Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.04652 · HTML: https://mlsanity.com/paper/2508.04652/

## Key facts

- Cited by 49 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 25 of its 58 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2506.24119/) (2025)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers](https://mlsanity.com/paper/2502.20379/) (2025)
- [An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2409.03052/) (2024)
- [Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting](https://mlsanity.com/paper/2303.14100/) (2023)
- [RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models](https://mlsanity.com/paper/2406.01983/) (2024)
- [Pruning Foundation Models for High Accuracy without Retraining](https://mlsanity.com/paper/2410.15567/) (2024)
- [Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2502.06060/) (2025)
- [How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs](https://mlsanity.com/paper/2507.08960/) (2025)
- [An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2405.06161/) (2024)

## Built on by (most cited first, 30 of 49)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards](https://mlsanity.com/paper/2510.08529/) (2025)
- [Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08847/) (2026)
- [Heterogeneous Agent Collaborative Reinforcement Learning](https://mlsanity.com/paper/2603.02604/) (2026)
- [Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.22995/) (2026)
- [Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation](https://mlsanity.com/paper/2511.02303/) (2025)
- [AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems](https://mlsanity.com/paper/2605.08715/) (2026)
- [LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents](https://mlsanity.com/paper/2602.01053/) (2026)
- [Counterfactual Credit Policy Optimization for Multi-Agent Collaboration](https://mlsanity.com/paper/2603.21563/) (2026)
- [Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation](https://mlsanity.com/paper/2510.15624/) (2025)
- [Exact Is Easier: Credit Assignment for Cooperative LLM Agents](https://mlsanity.com/paper/2603.06859/) (2026)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems](https://mlsanity.com/paper/2511.19368/) (2025)
- [Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic](https://mlsanity.com/paper/2601.21972/) (2026)
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://mlsanity.com/paper/2605.14089/) (2026)
- [Interactive Learning for LLM Reasoning](https://mlsanity.com/paper/2509.26306/) (2025)
- [AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.01586/) (2025)
- [Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces](https://mlsanity.com/paper/2605.02801/) (2026)
- [MARTI-MARS2: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation](https://mlsanity.com/paper/2602.07848/) (2026)
- [Scaling Multiagent Systems with Process Rewards](https://mlsanity.com/paper/2601.23228/) (2026)
- [Adaptive Robust Estimator for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2603.21574/) (2026)
- [Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis](https://mlsanity.com/paper/2604.14877/) (2026)
- [CosmoCore Affective Dream-Replay Reinforcement Learning for Code Generation](https://mlsanity.com/paper/2510.18895/) (2025)
- [Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate](https://mlsanity.com/paper/2601.22297/) (2026)
- [TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination](https://mlsanity.com/paper/2605.15207/) (2026)
- [When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs](https://mlsanity.com/paper/2605.24202/) (2026)
- [Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning](https://mlsanity.com/paper/2607.10836/) (2026)
- [MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking](https://mlsanity.com/paper/2607.17751/) (2026)

## Abstract (arXiv)

A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pretrained independently and not specifically optimized for coordination. Existing LLM fine-tuning frameworks rely on individual rewards, which require complex reward designs for each agent to encourage collaboration. To address these challenges, we model LLM collaboration as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. We develop a multi-agent, multi-turn algorithm, Multi-Agent Group Relative Policy Optimization (MAGRPO), to solve it, building on current RL approaches for LLMs as well as MARL techniques. Our experiments on LLM writing and coding collaboration demonstrate that fine-tuning MAS with MAGRPO enables agents to generate high-quality responses efficiently through effective cooperation. Our approach opens the door to using other MARL methods for LLMs and highlights the associated challenges. Our code is available at https://github.com/OpenMLRL/CoMLRL.