4 papers
Smoothness criterion for Fano orbifolds and bases of Lagrangian fibrations
Zhiyu Liu
We establish a smoothness criterion for Fano varieties with quotient singularities. As an application, we show that if is a Lagrangian fibration from a compact hyper-Kähle…
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference data. This limitation is particular…
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
Jiangwen Dong, Bo Li, Wanyu Lin
LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents t…
Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
Heyang Ma, Qirui Mi, Qipeng Yang +3
Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While mul…