作者位次 #5/6ICML 2026Poster· Social Aspects / Alignment
The Realignment Problem: When Right becomes Wrong in LLMs
Aakash Sen Sharma · Debdeep Sanyal · Manodeep Ray · Vivek Srivastava · Shirish Subhash Karande · Murari Mandal
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Aakash Sen Sharma · Debdeep Sanyal · Manodeep Ray · Vivek Srivastava · Shirish Subhash Karande · Murari Mandal
Aditya Namdev Kakade · Vivek Srivastava · Shirish Subhash Karande
Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a Gödel agent for compact models that performs policy repair via experience abstraction, turning failures into policy updates through a...
Neil Shah · Yash Sonkar · Shirish Subhash Karande · Vineet Gandhi