MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916009504407552 |
|---|---|
| author | Moore, H. Qi, S. Milojicic, D. Bash, C. Pasricha, S. |
| author_facet | Moore, H. Qi, S. Milojicic, D. Bash, C. Pasricha, S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13496 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters Moore, H. Qi, S. Milojicic, D. Bash, C. Pasricha, S. Distributed, Parallel, and Cluster Computing Machine Learning 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. |
| title | MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2605.13496 |