作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models
Meta Context Engineering via Agentic Skill Evolution
Haoran Ye · Xuning He · Vincent Arak · Haonan Dong · Guojie Song
智能体与工具OpenReview
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。
Haoran Ye · Xuning He · Vincent Arak · Haonan Dong · Guojie Song
Haonan Dong · Kehan Jiang · Haoran Ye · Wenhao Zhu · Zhaolu Kang · Guojie Song
Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or derivation errors; II) Inter-step level, involving oscilla...
Kehan Jiang · Haonan Dong · Zhaolu Kang · Zhengzhou Zhu · Guojie Song
Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternative solutions. Upon closer inspection, however, we uncover a surprising phenomenon: The First is The Best, where alte...