作者位次 #2/3NeurIPS 2026Poster
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Hanwen Liu · Yuanfu Sun · Qiaoyu Tan
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。
Hanwen Liu · Yuanfu Sun · Qiaoyu Tan
Yuanfu Sun · Kang Li · Pengkang Guo · Jiajin Liu · Qiaoyu Tan
Yuanfu Sun · Kang Li · Dongzhe Fan · Jiajin Liu · Qiaoyu Tan
Large Language Models (LLMs) increasingly rely on agentic capabilities—iterative retrieval, tool use, and decision-making—to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological de...