Search papers, labs, and topics across Lattice.
Shanghai AI Laboratory
2
1
2
1
LLMs struggle to navigate the complexities of real-world finance, as evidenced by a new benchmark revealing their limitations in timeliness, regulatory compliance, and tool selection across 760 financial APIs.
LLMs can now dynamically create and refine their own scientific tools at test time, outperforming agents stuck with static toolsets.
