Search papers, labs, and topics across Lattice.
Xi'an Jiaotong University
2
0
5
SeClaw reveals that existing benchmarks fall short in capturing the complexities of agent behavior, enabling a more nuanced evaluation of security risks in autonomous systems.
Chemical reaction diagram parsing, a notoriously difficult task for vision-language models, sees a significant leap in performance thanks to a new multi-agent framework that enforces chemical consistency.
