LAD'26 Fellows
Yimin Gao
University of Virginia
US
FlexNPU-Bench: Benchmarking Mechanism-Aware LLM Agents for Cross-Layer NPU Design
Subhadip Ghosh
.png/:/cr=t:8.07%25,l:0%25,w:100%25,h:83.85%25/rs=w:388,h:388,cg:true)
University of Minnesota, Twin Cities
US
FORGE-EDA: Flow Orchestration, Reasoning, Generation, and Evolution for End-to-End Analog/RF/mm-Wave Design Automation
Zesong Jiang
Arizona State University
US
PROBE: A Benchmark for Evaluating AI Agents in Physical-Design Reasoning and Optimization
Qiufeng Li
George Washington University
US
PDAgent-Bench-Pro: An End-to-End Benchmark for Agentic VLSI Physical Design
Pengju Liu
University of Minnesota, Twin Cities
US
Toward an AI Index for End-to-End Chip Design: Benchmarking and Improving LLM-Based Agents
Shang Liu
The Hong Kong University of Science and Technology
Hong Kong, SAR
Discovering Provably Better EDA Algorithms with AI Agents
Shvetank Prakash
Harvard University
US
Realizing Computer Architecture Agents for End-to-End Chip Design
Jiahe (Caroline) Shi
MIT
US
Reliable Multi-Agent Hardware Design with an Evidence-Conditioned Shared Design State
Bing-Yue Wu
Arizona State University
US
From Reports to Repairs: LLM-Driven Autonomous Agent for Design Rule Violation Fixing
Fenghua Wu
Texas A&M University
US
ProofCov: A Benchmark for Evaluating Specification-Driven Functional Coverage Generation
Hejia Zhang
University of California San Diego
US
HardwareRL: A Cross-Tool Training Harness for Self-Evolving LLM Agents in Chip Design