Search papers, labs, and topics across Lattice.
Southern University of Science and Technology
3
0
4
Agent memory breaks when models are forced to simultaneously interpret, update, and rewrite facts鈥攄ecoupling maintenance into explicit pairwise relation classification and role-based fusion yields up to a 29.8 percentage point accuracy leap.
LLMs struggle with statistical analysis, achieving only 68.6% accuracy on a new benchmark designed to rigorously test their capabilities.
Text world models can transform LLM-based agents from reactive responders into proactive planners, enhancing their performance in complex interactive tasks.
