HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation

TL;DR

HDLFORGE is a two-stage multi-agent framework that efficiently balances speed and accuracy in Verilog code generation by escalating to larger models only when necessary, incorporating formal verification to reduce bugs.

Contribution

The paper introduces a novel two-stage multi-agent system with adaptive escalation and formal verification for improved Verilog generation efficiency and accuracy.

Findings

Achieves 91.2% Pass@1 on VerilogEval Human with 50% lower latency.

Demonstrates significant accuracy improvements over medium-sized models.

Effectively reduces bug detection and repair time through formal agent integration.

Abstract

We present HDLFORGE, a two-stage multi-agent framework for automated Verilog generation that optimizes the trade-off between generation speed and accuracy. The system uses a compact coder with a medium-sized LLM by default (Stage A) and escalates to a stronger coder with an ultra-large LLM (Stage B) only when needed, guided by a calibrated score from inexpensive diagnostics including compilation, lint, and smoke tests. A key innovation is a counterexample-guided formal agent that converts bounded-model-checking traces into reusable micro-tests, significantly reducing bug detection time and repair iterations. The portable escalation controller can wrap existing Verilog LLM pipelines without modifying their internals. Evaluated on VerilogEval Human, VerilogEval V2, and RTLLM benchmarks, HDLFORGE demonstrates improved accuracy-latency trade-offs compared to single-stage systems through comprehensive analysis of wall-clock time distributions, escalation thresholds, and agent ablations. On VerilogEval Human and VerilogEval V2, HDLFORGE-Qwen achieves 91.2% and 91.8% Pass@1 with roughly 50% lower median latency, dramatically improving accuracy over other medium-sized models, and 97.2% Pass@5 on RTLLM.