Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation

• URL: http://arxiv.org/abs/2605.26498v1
• Date: Tue, 26 May 2026 03:21:32 GMT
• Title: Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation
• Abstract summary: We present Verilog-Evolve, a feedback-driven framework for versioned Verilog refinement and cross-session skill evolution.<n>For each task, Verilog-Evolve generates diverse minor candidates, evaluates them with executable feedback from functional simulation, Yosys synthesis, ABC timing proxy, and optional GEMM metrics.<n>To improve across tasks, the system maintains modular skill guidance, retrieves skills according to task and feedback context, and evolves candidate skills from logged histories.
• Score: 48.00513252649798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by functional checking. This is insufficient for practical RTL design, where useful Verilog must be correct, synthesizable, timing-conscious, and friendly to downstream hardware objectives. We present Verilog-Evolve, a feedback-driven framework for versioned Verilog refinement and cross-session skill evolution. For each task, Verilog-Evolve generates diverse minor candidates, evaluates them with executable feedback from functional simulation, Yosys synthesis, ABC timing proxy, and optional GEMM metrics, then promotes the best candidate into a major version under configurable scoring. To improve across tasks, the system maintains modular skill guidance, retrieves skills according to task and feedback context, and evolves candidate skills from logged histories through create/improve/skip decisions and verifier reports. Experiments on VerilogEval and mixed-precision GEMM tasks show that Verilog-Evolve improves final functional success and promotion stability while producing more downstream-friendly RTL under open-source synthesis, timing-proxy, and netlist-level GEMM objectives. Validation-gated skill evolution further improves GEMM downstream quality and achieves the best downstream score and GEMM held-out pass rate among the evaluated skill modes.

Related papers

• Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning [51.17262419591891]
  Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.<n>We present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning, and inference-time evolutionary search.
  arXiv  Detail & Related papers  (2026-07-24T04:35:29Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• Improve Large Language Model Systems with User Logs [31.771424321946782]
  UNO is a framework for improving large language models (LLMs) with user logs.<n>It distills logs into semi-structured rules and preference pairs, then employs query-and-feedback-driven clustering to manage data heterogeneity.<n> UNO achieves state-of-the-art effectiveness and efficiency, significantly outperforming Retrieval Augmented Generation (RAG) and memory-based baselines.
  arXiv  Detail & Related papers  (2026-02-06T07:55:26Z)
• Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation [4.723302382132762]
  silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations, and (iii) semantic drift as intent is reinterpreted across agent handoffs.<n>We propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs.
  arXiv  Detail & Related papers  (2026-01-27T16:10:23Z)
• 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)
• EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning [63.03672166010434]
  We introduce an evolutionary, task-agnostic, strategy-guided, executably-checkable data synthesis framework.<n>It jointly synthesizes problems, diverse candidate solutions, and verification artifacts.<n>It iteratively discovers strategies via a consistency-based evaluator that enforces agreement between human-annotated and strategy-induced checks.
  arXiv  Detail & Related papers  (2025-10-20T11:56:35Z)
• 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)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric [4.590930025882158]
  We propose VeriMind, an agentic LLM framework for Verilog code generation.<n>We introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement.<n> Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3%$ improvement on pass@k metric and $8.1%$ on pass@ARC metric.
  arXiv  Detail & Related papers  (2025-03-15T23:43:06Z)
• Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation [69.62857948698436]
  Recent advances in large language models (LLMs) have improved their performance on coding benchmarks.<n>However, improvement is plateauing due to the exhaustion of readily available high-quality data.<n>We propose Sol-Ver, a self-play solver-verifier framework that jointly improves a single model's code and test generation capacity.
  arXiv  Detail & Related papers  (2025-02-20T18:32:19Z)
• BetterV: Controlled Verilog Generation with Discriminative Guidance [11.162807308782751]
  We propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific runtime. BetterV has the ability to generate syntactically and functionally correct Verilog, which can outperform GPT-4 on the VerilogEval benchmark.
  arXiv  Detail & Related papers  (2024-02-03T08:00:12Z)

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.