作者位次 #5/6ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
Ammar Ahmed · Azal Ahmad Khan · Ayaan Ahmad · Sheng Di · Zirui Liu · Ali Anwar
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。
Ammar Ahmed · Azal Ahmad Khan · Ayaan Ahmad · Sheng Di · Zirui Liu · Ali Anwar
Zidi Xiong · Yuping Lin · Wenya Xie · Pengfei He · Zirui Liu · Jiliang Tang · Himabindu Lakkaraju · Zhen Xiang
Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper, we conduct an empirical study on how memory management choices impact the LLM agents’ behavior, especially their lon...