PDAGENT-BENCH: Characterizing, Grounding, and Architecting LLM Agents for VLSI Physical Design
For researchers and practitioners in VLSI design automation, this benchmark provides the first standardized evaluation for LLM agents in physical design, highlighting critical gaps in tool execution and long-horizon reasoning.
PDAGENT-BENCH introduces a benchmark for evaluating LLM/VLM agents in VLSI physical design, revealing that while models perform well on conceptual tasks, they struggle with tool-centric execution (e.g., 42.2% on script generation) and multi-stage reasoning.
Large Language Models and vision-language models have shown remarkable success in the front-end design of Very Large-Scale Integrated Circuits, yet their capabilities for VLSI physical design remain significantly underexplored. The primary cause is the lack of standardized benchmarks for evaluating agentic physical design workflows that require high-dimensional, multi-stage optimization under strict design constraints, coordinated interaction with diverse Electronic Design Automation tools, and iterative refinement. This work introduces PDAGENT-BENCH, a comprehensive and multi-dimensional benchmark for evaluating LLM/VLM-based agents across the physical design stack. PDAGENT-BENCH integrates both task-level assessment and workflow-level execution. The benchmark suite contains 353 curated problems that combine conceptual questions with real-world industrial artifacts, with expert-validated references and executable solutions. These tasks cover five key capability dimensions: foundational knowledge, report comprehension, root-cause analysis, script generation, and full-flow implementation. In addition, the benchmark provides a unified, human-aligned agentic physical design workflow framework that enables closed-loop evaluation of holistic physical design in realistic EDA environments. Experiments on 11 state-of-the-art models reveal that while modern LLMs/VLMs perform competitively on conceptual tasks, they remain substantially limited in tool-centric execution (e.g., 42.2% on Innovus script generation) and long-horizon, multi-stage reasoning. Our studies further show that human-skill-enhanced agentic workflows significantly improve end-to-end physical design performance. PDAGENT-BENCH establishes a standardized, reproducible, and realistic evaluation framework for advancing LLM/VLM-driven holistic physical design automation. We will open source the benchmark and framework soon.