作者位次 #3/5ICLR 2026Poster· Reinforcement Learning / Deep RL
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
Sanxing Chen · Xiaoyin Chen · Yukun Huang · Roy Xie · Bhuwan Dhingra
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。
Sanxing Chen · Xiaoyin Chen · Yukun Huang · Roy Xie · Bhuwan Dhingra
Yukun Huang · Sanxing Chen · Jian Pei · Manzil Zaheer · Bhuwan Dhingra
Yukun Huang · Leonardo F. R. Ribeiro · Momchil Hardalov · Bhuwan Dhingra · Markus Dreyer · Venkatesh Saligrama
Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers usually target general-domain atomic claims, and there is no benchmark to test whether such verifiers transfer to DRRs.Yet building such a benchma...