2 papers
cs.CL2026
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
Yuanfu Sun, Kang Li, Dongzhe Fan +2
Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Ye…
cs.CL2023
Bilevel Scheduled Sampling for Dialogue Generation
Jiawen Liu, Kan Li
Exposure bias poses a common challenge in numerous natural language processing tasks, particularly in the dialog generation. In response to this issue, researchers have devised var…