Search papers, labs, and topics across Lattice.
All authors are affiliated to School of Computing and Data Science, University of Hong Kong. Correspondence should be sent to Yuheng Lei and Ping Luo with email: leiyh@connect.hku.hk;pluo@hku.hk
1
1
3
5
LLMs can learn to generate high-quality symbolic world models by interacting with a multi-agent system that provides adaptive, behavior-aware feedback, closing the gap between static validation and interactive execution.
