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:20260402T024534Z
LOCATION:3008\, Level 3
DTSTART;TZID=America/Los_Angeles:20250624T161500
DTEND;TZID=America/Los_Angeles:20250624T163000
UID:dac_DAC 2025_sess157_RESEARCH1483@linklings.com
SUMMARY:Unlocking a New Rust Programming Experience: Fast and Slow Thinkin
 g with LLMs to Conquer Undefined Behaviors
DESCRIPTION:Renshuang Jiang, Pan Dong, Zhenling Duan, Yu Shi, Xiaoxiang Fa
 ng, Yan Ding, and Jun Ma (National University of Defense Technology); Shua
 i Zhao (Sun Yat-sen University); and Zhe Jiang (Southeast University)\n\nT
 o provide flexibility and low-level interaction capabilities, the ''unsafe
 '' tag in Rust is essential in many projects, but undermines memory safety
  and introduces Undefined Behaviors (UBs) that reduce safety. Eliminating 
 these UBs requires a deep understanding of Rust's safety rules and strong 
 typing. Traditional methods require depth analysis of code, which is labor
 ious and depends on knowledge design. The powerful semantic understanding 
 capabilities of LLM offer new opportunities to solve this problem. Althoug
 h existing large model debugging frameworks excel in semantic tasks, limit
 ed by fixed processes and lack adaptive and dynamic adjustment capabilitie
 s. Inspired by the dual process theory of decision-making (''Fast and Slow
  Thinking''), we present a LLM-based framework called RustBrain that autom
 atically and flexibly minimizes UBs in Rust projects. Fast thinking extrac
 ts features to generate solutions, while slow thinking decomposes, verifie
 s, and generalizes them abstractly. To apply verification and generalizati
 on results to solution generation, enabling dynamic adjustments and precis
 e outputs, RustBrain integrates two thinking through a feedback mechanism.
  Experimental results on Miri dataset show a 94.3% pass rate and 80.4% exe
 cution rate, improving flexibility and Rust projects safety.\n\nTopics: Sy
 stems\n\nTracks: SYS3: Embedded Software\n\nSession Chairs: Hoeseok Yang (
 Santa Clara University) and Younghyun Kim (Purdue University)\n\n
END:VEVENT
END:VCALENDAR