BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024532Z
LOCATION:3004\, Level 3
DTSTART;TZID=America/Los_Angeles:20250625T103000
DTEND;TZID=America/Los_Angeles:20250625T104500
UID:dac_DAC 2025_sess137_RESEARCH048@linklings.com
SUMMARY:ChatLS: Multimodal Retrieval-Augmented Generation and Chain-of-Tho
 ught for Logic Synthesis Script Customization
DESCRIPTION:Haisheng Zheng (Shanghai AI Laboratory) and Haoyuan WU and Zhu
 olun He (The Chinese University of Hong Kong)\n\nLarge Language Models (LL
 Ms) have demonstrated significant potential in automating the Electronic D
 esign Automation (EDA) process through effective integration with EDA tool
 s. This paper targets the customization of logic synthesis scripts, which 
 is crucial for accommodating the unique characteristics of each design in 
 the EDA workflow. The proposed framework, called ChatLS, integrates multim
 odal retrieval-augmented generation (RAG) and chain-of-thought (CoT) reaso
 ning, enabling LLMs to collaboratively analyze design features and precise
 ly customize synthesis scripts. Experimental results demonstrate that Chat
 LS has achieved superior performance in customizing synthesis scripts with
  commercial logic synthesis tool.\n\nTopics: EDA\n\nTracks: EDA5: RTL/Logi
 c Level and High-level Synthesis\n\nSession Chairs: Peipei Zhou (Brown Uni
 versity) and Cunxi Yu (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR