Search papers, labs, and topics across Lattice.
KAIST
3
0
6
A single capable verifier can dramatically improve terminal agent action reliability, achieving higher success rates at lower costs than simply generating more trajectories.
LLMs can overcome knowledge gaps in evolutionary search by dynamically co-evolving solutions and targeted web queries, leading to substantial gains in scientific discovery.
Extra test-time "thinking" cannot recover missing parametric facts, but teaching small reasoning models to recognize their own knowledge boundaries and selectively query larger models lets a 4B model outperform a 14B baseline at nearly a third of the serving cost.
