Skip to content
AI News HubLIVE
Original source2 min read

Alpha-RTL: Test-Time Training for RTL Hardware Optimization

Summary

Alpha-RTL (TTT-RTL) introduces the first per-design test-time training framework that lets an LLM policy adapt via executable EDA feedback for each specific RTL problem. It reduces geometric-mean PPA product by 65.1% on RTLLM v2.0 versus the reference, outperforming the strongest frozen-policy baseline (26.1%), and achieves a 59.4% ADP reduction on an industrial XuanTie C910 FPU unit. This signals a shift from functional correctness toward physically optimized LLM-based RTL generation.

SourcearXiv Machine LearningAuthor: Peilong Zhou, Zhirong Chen, Cangyuan Li, Haoyu Gao, Kaiyan Chang, Ziming Qu, Ying Wang
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.05253] Alpha-RTL: Test-Time Training for RTL Hardware Optimization

[Submitted on 3 Jun 2026]

Title:Alpha-RTL: Test-Time Training for RTL Hardware Optimization

View a PDF of the paper titled Alpha-RTL: Test-Time Training for RTL Hardware Optimization, by Peilong Zhou and 6 other authors

View PDF HTML (experimental)

Abstract:Large language models (LLMs) have shown increasing promise in generating

functionally correct register-transfer-level (RTL) hardware designs.

Recent systems improve further through EDA-integrated reinforcement

learning with syntax, simulation, and PPA rewards, but train a general

RTL generator before deployment while test-time approaches search with

a frozen policy. We instead perform reinforcement learning at test time,

allowing the LLM policy to adapt to executable EDA feedback for the

specific RTL problem at hand. We propose TTT-RTL, to our knowledge the

first per-design test-time training framework that closes the loop

between an LLM policy and an EDA pipeline for RTL optimization. TTT-RTL

samples candidate implementations, verifies them through syntax checking

and simulation, scores valid designs using synthesis-derived PPA product,

reuses high-reward variants through a PUCT-indexed design-state pool,

and updates the policy with an entropic policy-gradient objective. To

stabilize policy updates under sparse or plateaued rewards, we introduce

an adaptive KL-budget controller that adjusts the entropy constraint

using reference KL, effective sample size, and reward saturation signals.

On RTLLM v2.0 under Nangate 45nm, TTT-RTL reduces the geometric-mean

PPA product by 65.1% over the reference, outperforming the strongest

published frozen-policy agent baseline at 26.1%. On an industrial

XuanTie C910 FPU leading-zero-anticipation unit under Sky130, TTT-RTL

achieves a 59.4% ADP reduction, and ablations confirm that policy

adaptation, state reuse, and KL-budget control each contribute. These

results suggest that test-time training with executable EDA feedback can

move LLM-based RTL generation beyond functional correctness toward

physically optimized hardware.

Comments: 10 pages, 5 figures

Subjects:

Machine Learning (cs.LG)

ACM classes: I.2.6; B.7.1

Cite as: arXiv:2606.05253 [cs.LG]

(or arXiv:2606.05253v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.05253

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Peilong Zhou [view email] [v1] Wed, 3 Jun 2026 14:51:33 UTC (914 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Alpha-RTL: Test-Time Training for RTL Hardware Optimization, by Peilong Zhou and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

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, Media

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

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

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?)

Author

Venue

Institution

Topic

About arXivLabs

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.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Proposes TTT-RTL, the first per-design test-time training framework that closes the loop between an LLM policy and an EDA pipeline for RTL optimization.
  • Achieves a 65.1% reduction in geometric-mean PPA product on RTLLM v2.0 under Nangate 45nm, beating the strongest frozen-policy baseline at 26.1%.
  • Demonstrates a 59.4% ADP reduction on an industrial XuanTie C910 FPU leading-zero-anticipation unit under Sky130.
  • Introduces an adaptive KL-budget controller using reference KL, effective sample size, and reward saturation to stabilize policy updates.

Highlights and analysis are generated automatically and may contain errors. Check the original source.