BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Evo-MCTS: Gravitational-Wave Algorithm Search and Lessons for AI-A
 ssisted Physics
DTSTART;VALUE=DATE-TIME:20261025T060000Z
DTEND;VALUE=DATE-TIME:20261025T062000Z
DTSTAMP;VALUE=DATE-TIME:20261025T011231Z
UID:indico-contribution-3012@indico.itp.ac.cn
DESCRIPTION:Speakers: He Wang (ICTP-AP\, UCAS)\nThis talk presents Evo-MCT
 S (arXiv:2508.03661)\, a framework combining large language models\, Monte
  Carlo tree search\, and evolutionary optimization for automated algorithm
  discovery\, using gravitational-wave signal searches as a case study. Thr
 ough analyses of search trajectories and subsequent audits\, we examine ho
 w benchmark design influences optimization and how independent validation 
 and physical consistency checks can distinguish improvements in evaluation
  metrics from genuine scientific advances. Building on these findings\, we
  explore the potential of large language models in theoretical physics\, i
 ncluding the search for exact black-hole solutions through symbolic comput
 ation and formal verification in Lean\, and discuss broader opportunities 
 and challenges for AI-assisted scientific research.\n\nhttps://indico.itp.
 ac.cn/event/427/contributions/3012/
LOCATION:
URL:https://indico.itp.ac.cn/event/427/contributions/3012/
END:VEVENT
END:VCALENDAR