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.LG2025
MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
Guojiang Zhao, Zixiang Lu, Yutang Ge +13
Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods most…