Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Latent Poincaré Shaping for Agentic Reinforcement Learning
Hanchen Xia, Baoyou Chen, Zelin Zang +3
We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincaré latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and g…
cs.LG2026
SpecXMaster Technical Report
Yutang Ge, Yaning Cui, Hanzheng Li +15
Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and artificial intel…