Search papers, labs, and topics across Lattice.
Corresponding author
4
0
8
Agentic search methods only achieve a maximum Recall@100 of 31.4%, revealing a critical gap in current academic paper retrieval capabilities.
Claw-R1 transforms agentic RL by treating interaction data as valuable assets, enabling real-time inspection and curation for optimized training.
StepPO reveals that aligning policy optimization with agent decision-making steps can lead to superior performance in multi-turn interactions, outperforming traditional RL methods.
Table reasoning gets a reliability boost: TableMind++ uses uncertainty estimates to prune flawed plans and refine actions, outperforming prior models by synthesizing robust reasoning paths.
