Search papers, labs, and topics across Lattice.
Meituan, University of Science and Technology of China
2
0
4
Current LLM agents still struggle to infer and leverage user preferences from fragmented, real-world interactions, revealing a substantial gap between their capabilities and the demands of personalized decision-making.
LLM agents trained with simulated user and tool noise not only become more robust in messy real-world environments, but also surprisingly improve on clean, idealized benchmarks.
