cs.AINov 19, 2026

SiliconGym: A Versatile Reinforcement Learning Environment for Agentic EDA

Authors: Hejia Zhang, Sheng Lu, Yitong Ma, Zhongming Yu, Zhijing Wu, Wentao Ni, Chia-Tung Ho, Jishen Zhao

Organizations: University of California San Diego, La Jolla, CA, USA · Georgia Institute of Technology, Atlanta, GA, USA · NVIDIA, Santa Clara, CA, USA

Abstract

Reinforcement learning (RL) with electronic design automation (EDA) feedback is advancing large language models for hardware design and verification. Extending these gains to hardware-engineering agents requires environments that span tasks, preserve state across tool calls, and support large hierarchies alongside parallel rollouts. We present SiliconGym, the first versatile, cross-task and cross-toolchain RL environment for hardware design and verification. By decoupling versioned workspaces, budgeted execution, and acceptance-gated scoring, SiliconGym scales from module-level RTL, testbench, and PPA tasks to multi-round repository repair and full-hierarchy SoC flows. Streaming dispatch overlaps tool checks with generation, finishing a 256-answer RL batch 21.9% faster than native ChipSeek. Using interchangeable open-source and commercial backends, we show that open-source-trained functional correctness transfers cleanly to commercial simulation, while paired netlist evaluation reveals when open-source PPA gains survive commercial synthesis.

Figures & tables

Explore similar work

CardsList
  1. ChipOmni: A General-Purpose AI Agent for Electronic Design Automation

    Nov 9, 2026Pengkun Wang, Rui Mao, Zhe Zhao +9Electronic Design AutomationAI Agent Architecture

  2. Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows

    Jul 20, 2026Jinyuan Deng, Zhengrui Chen, Xufeng Wei +4Electronic Design AutomationLLM Agent Evaluation

  3. Automatic Generation of High-Performance RL Environments

    Mar 12, 2026Seth Karten, Rahul Dev Appapogu, Chi JinSimulation-Based RLReinforcement Learning