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:20260730T152640Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T173100
DTEND;TZID=America/Los_Angeles:20260728T173200
UID:dac_DAC 2026_sess317_RESEARCH535@linklings.com
SUMMARY:MappingEvolve: LLM-Driven Code Evolution for Technology Mapping
DESCRIPTION:Rongliang Fu, Yi Liu, Qiang Xu, and Tsung-Yi Ho (The Chinese U
 niversity of Hong Kong)\n\nTechnology mapping is a critical yet challengin
 g stage in logic synthesis. While Large Language Models (LLMs) have been a
 pplied to generate optimization scripts, their potential for core algorith
 m enhancement remains untapped. We introduce MappingEvolve, an open-source
  framework that pioneers the use of LLMs to directly evolve technology map
 ping code. Our method abstracts the mapping process into distinct optimiza
 tion operators and employs a hierarchical agent-based architecture, compri
 sing a Planner, Evolver, and Evaluator, to guide the evolutionary search. 
 This structured approach enables strategic and effective code modification
 s. Experiments show our method significantly outperforms direct evolution 
 and strong baselines, achieving 10.04\% area reduction versus ABC and 7.93
 \% versus mockturtle, with 46.6\%--96.0\% $S_{overall}$ improvement on EPF
 L benchmarks, while explicitly navigating the area--delay trade-off. We ha
 ve open-sourced our framework to foster reproducibility and further resear
 ch.\n\nTrack: EDA7-II. Physical Design and Verification, Design\n\nSession
  Chairs: Christian Pilato (Politecnico di Milano); Mohsen Imani (Universit
 y of California, Irvine); Flavio Ponzina (San Diego State University); Ami
 n Farshidi (Cadence Design Systems, Inc.); Yonggan Fu (Georgia Institute o
 f Technology, NVIDIA); Dimitrios Tsaras (Huawei, Hong Kong University of S
 cience and Technology (HKUST)); Anh Nguyen (Fujitsu Limited); Ruiyang Qin 
 (Villanova University); Jiliang Zhang (Hunan University); Meng Li (Peking 
 University); and Rassul Bairamkulov (Advanced Micro Devices (AMD))\n\n
END:VEVENT
END:VCALENDAR
