HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
arXiv:2609.30270 (cs)
[Submitted on 14 Jul 2026]
Title:HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference
Authors:Simran Koul
View a PDF of the paper titled HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference, by Simran Koul
View PDF
HTML (experimental)
Abstract:On-device inference with small language models keeps user data local, works offline, and incurs no per-query cost, so the on-device tier is preferred when it is adequate. It is thermally constrained, however, and I find the constraint is sharper than a slowdown: on a flagship Snapdragon device, sustained on-device generation destabilizes the GPU inference runtime, which crashes or silently wedges after a few consecutive queries. The failure lies in the current toolchain (OpenCL kernel compilation and long-prompt prefill on the mobile GPU), recurs even when the device is cool, and is worst for long generations. Multi-tier routers across on-device, edge, and cloud models can relieve this pressure, but existing routers are thermal-blind and typically evaluated in simulation or on non-mobile hardware. I present HybridInfer, a thermal-aware reinforcement-learning router for a three-tier hierarchy (on-device Llama 3.2 3B, edge Llama 3.1 8B with retrieval, cloud GPT-4o) that uses the phone's thermal headroom and a query-complexity estimate as state and selects a tier by an offline-trained Q-learning policy. Its reward trades quality against latency, cost, and a thermal penalty, plus a locality bonus crediting on-device execution. I show this bonus is a precondition for thermal-aware routing: without it the optimal policy offloads every query. On a real Android benchmark of 210 prompts, the learned router attains significantly higher quality than two hand-tuned heuristics (paired Wilcoxon, p < 0.02) at the lowest cost of any adaptive condition. Always-on-device conditions match per-query quality on servable queries but are three to six times slower and fail on long queries, so routing wins on latency, reliability, and coverage rather than quality. To my knowledge this is the first use of on-device thermal headroom to select among LLM inference tiers of differing capability on real hardware.
| Comments: | 8 pages, 3 figures. Evaluated on real Android hardware (Samsung Galaxy S25+, Snapdragon 8 Elite). Workload of 210 prompts with frozen gold references. Android measurement harness and full routing/evaluation pipeline released for replication at this https URL |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | I.2.7; I.2.6; C.2.4 |
| Cite as: | arXiv:2609.30270 [cs.LG] |
| (or arXiv:2609.30270v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.30270
arXiv-issued DOI via DataCite
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference, by Simran Koul
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Algebraic Integer Quantization for Machine Learning Applications
Oct 12
-
CircuitTree: Composing Circuits into A Syllable Transcriber
Oct 12
-
Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights
Oct 12
-
GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
Oct 12
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.