Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

Hugging Face Daily Papers Papers

Summary

Rule2DRC introduces a large-scale benchmark for DRC script synthesis with 1,000 tasks and 13,921 evaluation layouts, and proposes SplitTester, which uses execution feedback to improve program selection and functional correctness.

Manufacturable chip layouts must satisfy thousands of geometry-based design rules, and design rule checking (DRC) enforces them by running executable DRC scripts on layouts. Translating natural language rules into correct DRC scripts is labor-intensive and requires specialized expertise, motivating LLM agents for DRC script synthesis and debugging. However, existing benchmarks have small evaluation sets and often evaluate scripts by code similarity rather than execution correctness, and prior machine learning-based methods either ignore execution feedback or require labeled test layouts as agent's input. To this end, we introduce Rule2DRC, a large-scale benchmark for DRC script coding agents with 1,000 rule-to-script tasks and 13,921 evaluation chip layouts for execution-based scoring. Rule2DRC provides an evaluation pipeline that measures functional correctness via DRC execution outcomes without requiring evaluation layouts as input to the agent. We also propose SplitTester, a tester agent for program selection that uses execution feedback to generate discriminative test cases and separate previously indistinguishable candidate scripts, substantially improving Best-of-N selection performance in this domain. We release the code at https://github.com/snu-mllab/Rule2DRC.
Original Article
View Cached Full Text

Cached at: 05/22/26, 06:20 PM

Paper page - Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

Source: https://huggingface.co/papers/2605.15669

Abstract

Rule2DRC introduces a large-scale benchmark for DRC script synthesis with 1,000 rule-to-script tasks and 13,921 evaluation layouts, along with SplitTester which improves program selection through execution-based feedback.

Manufacturablechip layoutsmust satisfy thousands of geometry-based design rules, anddesign rule checking(DRC) enforces them by running executableDRC scriptson layouts. Translatingnatural language rulesinto correctDRC scriptsis labor-intensive and requires specialized expertise, motivating LLM agents forDRC script synthesisand debugging. However, existing benchmarks have small evaluation sets and often evaluate scripts by code similarity rather than execution correctness, and prior machine learning-based methods either ignoreexecution feedbackor require labeled test layouts as agent’s input. To this end, we introduce Rule2DRC, a large-scale benchmark for DRC script coding agents with 1,000 rule-to-script tasks and 13,921 evaluationchip layoutsfor execution-based scoring. Rule2DRC provides anevaluation pipelinethat measuresfunctional correctnessvia DRC execution outcomes without requiring evaluation layouts as input to the agent. We also propose SplitTester, a tester agent forprogram selectionthat usesexecution feedbackto generate discriminative test cases and separate previously indistinguishable candidate scripts, substantially improvingBest-of-N selectionperformance in this domain. We release the code at https://github.com/snu-mllab/Rule2DRC.

View arXiv pageView PDFGitHub0Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.15669 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.15669 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.15669 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents

arXiv cs.AI

This paper introduces Agentick, a unified benchmark for evaluating general sequential decision-making agents across RL, LLM, and VLM paradigms. It provides 37 procedurally generated tasks and reveals that no single approach currently dominates, highlighting significant room for improvement in agent autonomy.