mlsanityData to 14 Oct 2026

AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization

arXiv 2512.23742 ↗First posted 26 Dec 2025cs.SE cs.AIcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

With the continued scaling of advanced technology nodes, the design-technology co-optimization (DTCO) paradigm has become increasingly critical, rendering efficient device design and optimization essential. In the domain of TCAD simulation, however, the scarcity of open-source resources hinders language models from generating valid TCAD code. To overcome this limitation, we construct an open-source TCAD dataset curated by experts and fine-tune a domain-specific model for TCAD code generation. Building on this foundation, we propose AgenticTCAD, a natural language - driven multi-agent framework that enables end-to-end automated device design and optimization. Validation on a 2 nm nanosheet FET (NS-FET) design shows that AgenticTCAD achieves the International Roadmap for Devices and Systems (IRDS)-2024 device specifications within 4.2 hours, whereas human experts required 7.1 days with commercial tools.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 12 of its 33 references that are in the map. First posted on arXiv 26 Dec 2025.

Builds on

12 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ChatEDA: A Large Language Model Powered Autonomous Agent for EDA20 Aug

Other references · 11

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2024A Survey on Large Language Models for Code Generationcited by 658
  4. 2023RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Modelscited by 100
  5. 2024OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflectioncited by 56
  6. 2024ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Modelscited by 44
  7. 2024RTLRewriter: Methodologies for Large Models aided RTL Code Optimizationcited by 31
  8. 2024MEIC: Re-thinking RTL Debug Automation using LLMscited by 25
  9. 2024LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Designcited by 25
  10. 2025A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design and EDAcited by 17
  11. 2024Large Language Model (LLM) for Standard Cell Layout Design Optimizationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Agentic Electronic Design Automation: A Handoff Perspectivecited by 0
  2. 2026Agentic TCAD Calibration Workflow for Oxide Semiconductor Transistorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
  2. 2026CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
  3. 2026Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
  4. 2025ORFS-agent: Tool-Using Agents for Chip Design Optimization
  5. 2025ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation
  6. 2025HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization
  7. 2026Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation
  8. 2026AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents