作者位次 #4/5NeurIPS 2026Poster
Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
Wenhao Deng · Tian Xia · Yuru Jiang · Joemon M. Jose · Tailin Wu
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。
Wenhao Deng · Tian Xia · Yuru Jiang · Joemon M. Jose · Tailin Wu
Junchen Fu · Xuri Ge · Alexandros Karatzoglou · Ioannis Arapakis · Suzan Verberne · Joemon M. Jose · Zhaochun Ren
Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content. Most methods treat SIDs as predefined and train recommenders under static indexing. In practice, SIDs are optimized only for content reconstruction rath...