作者位次 #6/8ICML 2026Poster· Deep Learning / Large Language Models
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Zhaoyang Wang · Canwen Xu · Boyi Liu · Yite Wang · Siwei Han · Zhewei Yao · Huaxiu Yao · Yuxiong He
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。
Zhaoyang Wang · Canwen Xu · Boyi Liu · Yite Wang · Siwei Han · Zhewei Yao · Huaxiu Yao · Yuxiong He
Youngwon Lee · seung-won hwang · Zhewei Yao · Yuxiong He
Retrieval-augmented generation needs generation to follow retrieved evidence across shifting domains and prompt layouts, but training a new stronger model per task is costly. To this end, we propose GRAD, an adaptive decoding-time framework that keeps the base generator fixed and composes small,...
Zhewei Yao · Guoheng Sun · Łukasz Borchmann · Zheyu Shen · Minghang Deng · Bohan Zhai · Hao Zhang · Ang Li · Yuxiong He
Translating natural language into SQL (Text2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improved fluency in SQL generation, producing correct and executable SQL, particular...
Youngwon Lee · seung-won hwang · Ruofan Wu · Feng Yan · Danmei Xu · Moutasem Akkad · Zhewei Yao · Yuxiong He
We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc prunin...
Hojae Han · Yeonseok Jeong · seung-won hwang · Zhewei Yao · Yuxiong He
Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limitations. First, they often score functionally equivalent SQL queries inconsistently despite identical execution results. Second, ranking cannot reco...