# MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters

arXiv: https://arxiv.org/abs/2605.13496 · HTML: https://mlsanity.com/paper/2605.13496/

## Key facts

- Cited by 1 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 14 of its 37 references that are in the map.
- First posted on arXiv 13 May 2026.

## 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, 14 of 14)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference](https://mlsanity.com/paper/2503.08311/) (2025)
- [PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services](https://mlsanity.com/paper/2405.14636/) (2024)
- [The Unseen AI Disruptions for Power Grids: LLM-Induced Transients](https://mlsanity.com/paper/2409.11416/) (2024)
- [Energy and Network Aware Workload Management for Geographically Distributed Data Centers](https://mlsanity.com/paper/2106.00066/) (2021)
- [Sustainable Carbon-Aware and Water-Efficient LLM Scheduling in Geo-Distributed Cloud Datacenters](https://mlsanity.com/paper/2505.23554/) (2025)
- [CASA: A Framework for SLO and Carbon-Aware Autoscaling and Scheduling in Serverless Cloud Computing](https://mlsanity.com/paper/2409.00550/) (2024)

## Built on by (most cited first, 1 of 1)

- [Dissecting the Carbon-SLO Tension in Geo-Distributed LLM Serving](https://mlsanity.com/paper/2610.14571/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enterprise services. LLM inference requests in particular account for up to 90% of total LLM lifecycle energy use, dwarfing training energy costs. The rising volume of LLM inference requests is increasing environmental footprints, particularly carbon emissions and water consumption. To improve sustainability for LLM inference serving in cloud datacenter environments, we propose a novel multi-agent game-theoretic reinforcement learning framework called MARLIN to co-optimize time-to-first token (TTFT), carbon emissions, water usage, and energy costs associated with LLM inference. MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.