Search papers, labs, and topics across Lattice.
4
0
6
8
Current autonomous agents excel at practical problem-solving but often lack true methodological innovation, revealing critical gaps in their development as independent researchers.
Harness-assisted data synthesis boosts LLM forecasting performance by reducing temporal leakage and increasing sampling efficiency, leading to superior predictive capabilities.
Automatic harness evolution may not be the silver bullet for LLM performance it was thought to be, often lagging behind simpler scaling methods.
Agentic search gets a meta-RL boost: MR-Search learns to self-reflect and adapt search strategies across episodes, significantly outperforming standard RL baselines.
