Evaluating Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone Variable-Air-Volume Control
cs.LG, cs.SY, eess.SY
Submitted: 2026-07-30
Updated: 2026-10-30
Comments: Revised and expanded version. 46 pages, 18 figures. Published in Energy and AI
Journal ref: Energy and AI 26 (2026) 100933
DOI: 10.1016/j.egyai.2026.100933
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Pre-Trained Large Language Models for Industrial Control
- ThermoLLM: LLM-Based Multi-Zone HVAC Control with a Spatiotemporal Context
- Hierarchical Control Framework Integrating LLMs with RL for Decarbonized HVAC Operation
- Understanding R1-Zero-Like Training: A Critical Perspective
- Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control
- Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification
- gpt-oss-120b & gpt-oss-20b Model Card
- Reasoning Models Don't Always Say What They Think
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis