BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//speaker//BLGYT3
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-eu-summit-2026-GJMGHA@cfp.riscv-europe.org
DTSTART;TZID=CET:20260610T142000
DTEND;TZID=CET:20260610T143000
DESCRIPTION:Functional verification remains a critical bottleneck in modern
  IC development cycles. However\, traditional methods\, including constrai
 ned-random and formal verification\, struggle to keep pace with the growin
 g complexity of modern semiconductor designs.\n\nWhile recent advances in 
 Large Language Models (LLMs) have shown promise in code generation and tas
 k automation\, significant challenges hinder the realization of end-to-end
  functional verification automation.\nThese challenges include (i) limited
  accuracy in generating Verilog/SystemVerilog verification code\, (ii) the
  fragility of LLMs when executing complex\, multi-step verification workfl
 ows\, and (iii) the difficulty of maintaining verification consistency acr
 oss specifications\, coverage models\, and test cases throughout the workf
 low.\n\nTo address these challenges\, we propose UCAgent\, an end-to-end a
 gent that automates hardware block-level functional verification based on 
 three core mechanisms.\nFirst\, we establish a pure Python verification en
 vironment using Picker and Toffee to avoid relying on LLM-generated System
 Verilog verification code.\nSecond\, we introduce a configurable 31-stage 
 fine-grained verification workflow to guide the LLM\, where each stage is 
 verified by an automated checker.\nFurthermore\, we propose a Verification
  Consistency Labeling Mechanism (VCLM) that assigns hierarchical labels to
  LLM-generated artifacts\, improving the reliability and traceability of v
 erification.\n\nExperimental results show that UCAgent can complete end-to
 -end automated verification on multiple modules\, including the UART\, FPU
 \, and integer divider modules\, achieving up to 98.5\\% code coverage and
  up to 100\\% functional coverage. UCAgent also discovers previously unide
 ntified design defects in realistic designs\, demonstrating its practical 
 potential.
DTSTAMP:20260522T162405Z
LOCATION:Poster Island A
SUMMARY:UCAgent: An End-to-End Agent for Block-Level Functional Verificatio
 n - Junyue Wang\, YanPi\, Fangyuan Song\, yaozhicheng\, wangsa
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/GJMGHA/
END:VEVENT
END:VCALENDAR