mlsanityData to 7 Oct 2026

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

arXiv 2511.00116 ↗First posted 31 Oct 2025cs.LG cs.AI cs.MAcited by 3

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

Abstract (arXiv)

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 11 of its 40 references that are in the map. First posted on arXiv 31 Oct 2025.

Builds on

11 of 40 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  3. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  4. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
  5. 2024Benchmarking and Dissecting the Nvidia Hopper GPU Architecturecited by 23
  6. 2021A Machine Learning Framework for Real-time Inverse Modeling and Multi-objective Process Optimization of Composites for Active Manufacturing Controlcited by 9
  7. 2024SustainDC: Benchmarking for Sustainable Data Center Controlcited by 8
  8. 2023PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainabilitycited by 6
  9. 2024Carbon Footprint Reduction for Sustainable Data Centers in Real-Timecited by 4
  10. 2024A Digital Twin Framework for Liquid-cooled Supercomputers as Demonstrated at Exascalecited by 3
  11. 2025Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusterscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Fast 3D Surrogate Modeling for Data Center Thermal Managementcited by 0
  2. 2026DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rulescited by 0
  3. 2026Artificial Intelligence for Energy Optimization in Data Centerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Data Center Cooling System Optimization Using Offline Reinforcement Learning
  2. 2026Coordinated Cooling and Compute Management for AI Datacenters ↗
  3. 2026Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet
  4. 2026Offline Reinforcement-Learning-Based Power Control for Application-Agnostic Energy Efficiency
  5. 2026Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control
  6. 2026Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement Learning
  7. 2026MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters
  8. 2025ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents