Search papers, labs, and topics across Lattice.
4
0
6
3
A self-evolving framework achieves up to 15.5 percentage points in performance gains by intelligently refining the agent's harness without altering the underlying model.
Ability-guided transfer reveals that agents struggle to consistently leverage learned experiences, challenging the effectiveness of current self-evolution methods.
LLMs excel in binary classifications but struggle dramatically with complex psychiatric diagnoses, revealing critical gaps in AI-assisted mental health tools.
Fragmented retrieval in long-term conversational agents is solved by HyperMem, which uses hypergraphs to model high-order associations between memories, achieving state-of-the-art performance.
