一作ICLR 2026Poster
THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS
Zhichao Wang · Dongyang Ma · Xinting Huang · Deng Cai · Tian Lan · Jiahao Xu · Haitao Mi · Xiaoying Tang · Yan Wang
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。
Zhichao Wang · Dongyang Ma · Xinting Huang · Deng Cai · Tian Lan · Jiahao Xu · Haitao Mi · Xiaoying Tang · Yan Wang
Haoyue Liu · Zhichao Wang · Yongxin Guo · Haoran Shou · Xiaoying Tang
Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adapt...