The original title is: "VeriTrace: Human-Like Temporal Exploration Completes Agentic Action Space"

Short summary

VeriTrace is a multi-agent system that achieves 100% Pass@1 on VerilogEval-V2 for automated Verilog RTL generation, a first for this benchmark. It introduces Agentic Temporal Exploration, giving an Inspector agent full control over signal selection, time-window bounds, and iteration depth during debugging. On a shared Claude Sonnet 4.0 backbone, it outperforms the strongest baseline by +5.1%, closing the final accuracy gap through hypothesis-driven root-cause analysis.

• •VeriTrace achieves 100% Pass@1 on VerilogEval-V2, first system to do so
• •Introduces Agentic Temporal Exploration for complete debugging action space
• •Outperforms strongest baseline by +5.1% using Claude Sonnet 4.0

Generated with AI, which can make mistakes.