EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation

• URL: http://arxiv.org/abs/2511.12033v1
• Date: Sat, 15 Nov 2025 05:00:07 GMT
• Title: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
• Authors: Jiahe Shi, Zhengqi Gao, Ching-Yun Ko, Duane Boning,
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach to bridge the gap between model capability and real-world RTL design.<n>We present EARL, an Entropy-Aware Reinforcement Learning framework for Verilog generation.
• Score: 7.512194032034432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap remains between model capability and the demands of real-world RTL design, including syntax errors, functional hallucinations, and weak alignment to designer intent. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach to bridge this gap, as hardware provides executable and formally checkable signals that can be used to further align model outputs with design intent. However, in long, structured RTL code sequences, not all tokens contribute equally to functional correctness, and naïvely spreading gradients across all tokens dilutes learning signals. A key insight from our entropy analysis in RTL generation is that only a small fraction of tokens (e.g., always, if, assign, posedge) exhibit high uncertainty and largely influence control flow and module structure. To address these challenges, we present EARL, an Entropy-Aware Reinforcement Learning framework for Verilog generation. EARL performs policy optimization using verifiable reward signals and introduces entropy-guided selective updates that gate policy gradients to high-entropy tokens. This approach preserves training stability and concentrates gradient updates on functionally important regions of code. Our experiments on VerilogEval and RTLLM show that EARL improves functional pass rates over prior LLM baselines by up to 14.7%, while reducing unnecessary updates and improving training stability. These results indicate that focusing RL on critical, high-uncertainty tokens enables more reliable and targeted policy improvement for structured RTL code generation.

Related papers

• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation [47.82802346420197]
  We propose Signal-Aware Learning for Verilog code generation (QiMeng-SALV)<n>We verify the functional correctness of signals in generated module by comparing with that of reference module in the training data.<n>Finally, we introduce signal-aware DPO which is optimized on the correct signal-level code segments.
  arXiv  Detail & Related papers  (2025-10-22T06:58:07Z)
• VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning [32.974199255760944]
  We introduce a reinforcement learning framework tailored for Verilog code generation.<n>To tackle the problem of sparse and noisy reward signals, we propose a Trace-back based Rescore mechanism.<n>To mitigate catastrophic forgetting and overfitting during RL fine-tuning, we introduce a sample-balanced weighting strategy.
  arXiv  Detail & Related papers  (2025-08-25T20:20:44Z)
• ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning [32.11086992218369]
  ChipSeek-R1 is a hierarchical reward-driven reinforcement learning framework for large language models.<n>It generates RTL code that is both functional correctness and PPA-optimized.<n>On the RTLLM benchmark, ChipSeek-R1 generated 27 RTL designs surpassing the PPA metrics of the original human-written code.
  arXiv  Detail & Related papers  (2025-07-07T08:08:20Z)
• RTL++: Graph-enhanced LLM for RTL Code Generation [0.0]
  Traditional register transfer level (RTL) design methods are manual, time-consuming, and prone to errors.<n>Open-source models offer alternatives; however, they frequently fall short in quality/correctness.<n>This paper proposes RTL++, a first-of-its-kind LLM-assisted method for RTL code generation.
  arXiv  Detail & Related papers  (2025-05-11T00:17:26Z)
• AIvril: AI-Driven RTL Generation With Verification In-The-Loop [0.7831852829409273]
  Large Language Models (LLMs) are computational models capable of performing complex natural language processing tasks. This paper introduces AIvril, a framework designed to enhance the accuracy and reliability of RTL-aware LLMs.
  arXiv  Detail & Related papers  (2024-09-03T15:07:11Z)
• GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval [80.96706764868898]
  We present a new Low-light Image Enhancement (LLIE) network via Generative LAtent feature based codebook REtrieval (GLARE) We develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook. Experiments confirm the superior performance of GLARE on various benchmark datasets and real-world data.
  arXiv  Detail & Related papers  (2024-07-17T09:40:15Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Certified Reinforcement Learning with Logic Guidance [78.2286146954051]
  We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs) The algorithm is guaranteed to synthesise a control policy whose traces satisfy the specification with maximal probability.
  arXiv  Detail & Related papers  (2019-02-02T20:09:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.