3 papers
cs.CL2025
Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
Zhe Hu, Jing Li, Zhongzhu Pu +2
Vision Language Models exhibit impressive performance for various tasks, yet they often lack the sophisticated situational reasoning required for complex decision-making. This pape…
cs.CL2025
Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation
Zhe Hu, Hou Pong Chan, Jing Li +1
Writing persuasive arguments is a challenging task for both humans and machines. It entails incorporating high-level beliefs from various perspectives on the topic, along with deli…
cs.CL2024
AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction
Zhe Hu, Hou Pong Chan, Yu Yin
Argument generation is a challenging task in natural language processing, which requires rigorous reasoning and proper content organization. Inspired by recent chain-of-thought pro…